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

    Neuronpedia

    INDEX
    Explanations

    mentions of competition and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /
    -0.57
     /
    -0.51
     and
    -0.47
     féd
    -0.44
    .
    -0.43
     '
    -0.42
     "
    -0.41
    ↵
    -0.40
     Some
    -0.40
    end
    -0.40
    POSITIVE LOGITS
    oredCriteria
    0.82
    同じく
    0.82
    Попис
    0.81
     Efq
    0.81
    êques
    0.80
     myſelf
    0.79
     raiſ
    0.77
     fubject
    0.76
     himſelf
    0.76
     itſelf
    0.75
    Act Density 0.396%

    No Known Activations