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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to individuals with specific characteristics or needs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acerb
    -0.15
    gba
    -0.14
    iliary
    -0.14
    illez
    -0.14
     edil
    -0.14
     Sass
    -0.13
     alphabet
    -0.13
     '%$
    -0.13
    áš
    -0.13
    ãİ
    -0.13
    POSITIVE LOGITS
     otherwise
    0.18
    otherwise
    0.15
     Barrel
    0.15
    olly
    0.14
     Otherwise
    0.14
     themselves
    0.14
    843
    0.14
     Kidd
    0.14
    utherland
    0.14
     previously
    0.14
    Act Density 0.110%

    No Known Activations