© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1581
    Prev
    Next
    INDEX
    Explanations

    assertions or statements of identity related to actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ゼウス
    -0.79
    ICO
    -0.74
    avi
    -0.72
    ateurs
    -0.72
    stretched
    -0.69
    hess
    -0.67
    daq
    -0.66
     0004
    -0.66
    EVA
    -0.66
    ubis
    -0.66
    POSITIVE LOGITS
     resentment
    0.73
     offending
    0.69
     wound
    0.68
     doubtless
    0.68
     sanity
    0.67
     debt
    0.67
     embodied
    0.66
     undoubtedly
    0.63
     unpredict
    0.63
     Responsibility
    0.62
    Activations Density 0.176%

    No Known Activations