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

    Neuronpedia

    INDEX
    Explanations

    headings or section titles in the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abaj
    -0.17
    istrat
    -0.17
    ag
    -0.15
    stab
    -0.15
    yst
    -0.15
    ensi
    -0.15
    elta
    -0.15
    ycz
    -0.15
    ichen
    -0.14
    anna
    -0.14
    POSITIVE LOGITS
    ream
    0.16
    ingham
    0.15
    梨
    0.15
    Continue
    0.15
    大åĪ©
    0.14
    327
    0.14
    .private
    0.14
    nek
    0.14
    лÑĥг
    0.13
    Mathf
    0.13
    Act Density 0.007%

    No Known Activations