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

    Neuronpedia

    INDEX
    Explanations

    punctuations and dialogue elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     civilian
    -0.16
    ropri
    -0.15
    eniable
    -0.14
    atta
    -0.14
    FromString
    -0.14
    íıIJ
    -0.14
    ioso
    -0.14
     Perr
    -0.13
    _NE
    -0.13
    /md
    -0.13
    POSITIVE LOGITS
    omik
    0.16
     stop
    0.15
     Gregg
    0.15
     full
    0.15
    .stop
    0.15
     complet
    0.15
     finish
    0.14
     Roch
    0.14
    tat
    0.14
    Descriptions
    0.14
    Act Density 0.105%

    No Known Activations