Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    web links or handles, specifically with multiple characters, numbers, and unusual punctuation

    oai_token-act-pair · gpt-3.5-turbo

    URLs and links

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ÂŃ
    -0.71
     afore
    -0.69
    ãĢij
    -0.66
     caring
    -0.61
     corrections
    -0.60
    -0.60
     wanting
    -0.57
     misrepresent
    -0.57
     franchise
    -0.57
     notebooks
    -0.56
    POSITIVE LOGITS
    zx
    1.23
    zn
    1.19
    FK
    1.16
    ql
    1.16
    qv
    1.13
    Iv
    1.12
    YR
    1.11
    yx
    1.11
    nv
    1.09
    zl
    1.09
    Act Density 0.056%

    No Known Activations