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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "won't"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nts
    -0.18
    abet
    -0.17
    ankan
    -0.15
    inction
    -0.15
    ames
    -0.15
     Thick
    -0.14
    ents
    -0.14
    ickers
    -0.14
    GLenum
    -0.14
    nton
    -0.14
    POSITIVE LOGITS
    uve
    0.16
    ubic
    0.15
    ç¨
    0.14
    зв
    0.14
    cura
    0.14
     stip
    0.14
    yte
    0.14
     Extras
    0.13
     Expert
    0.13
    chwitz
    0.13
    Act Density 0.000%

    No Known Activations