© 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. 2634
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty or the unknown

    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
    bees
    -0.67
    hire
    -0.65
     contend
    -0.64
     whisper
    -0.64
    roe
    -0.63
    neys
    -0.61
     pond
    -0.61
    seek
    -0.60
     pursu
    -0.59
     estates
    -0.58
    POSITIVE LOGITS
     exactly
    0.76
     whether
    0.72
     precisely
    0.68
     how
    0.66
    actly
    0.65
     Exactly
    0.63
    icular
    0.62
     beforehand
    0.61
     specifics
    0.61
    atform
    0.60
    Activations Density 0.064%

    No Known Activations