© 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. 2630
    Prev
    Next
    INDEX
    Explanations

    phrases that express a sense of near certainty or approximations

    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
    ESE
    -0.99
    アル
    -0.84
    ゼウス
    -0.84
    aturation
    -0.82
    ィ
    -0.79
    ォ
    -0.77
    Slow
    -0.77
    м
    -0.76
    aeda
    -0.76
    ANGE
    -0.75
    POSITIVE LOGITS
     thereto
    0.72
     spherical
    0.71
     universally
    0.71
     guarantees
    0.70
     incom
    0.70
     rim
    0.69
     invariably
    0.69
     expressly
    0.68
     dome
    0.68
    ocally
    0.67
    Activations Density 0.029%

    No Known Activations