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

    Neuronpedia

    INDEX
    Explanations

    elements related to societal dynamics and human relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.79
     itſelf
    -0.75
     himſelf
    -0.69
     auffi
    -0.68
     Efq
    -0.68
    <bos>
    -0.65
     Jefus
    -0.64
     fince
    -0.63
     ſche
    -0.63
     Monfieur
    -0.61
    POSITIVE LOGITS
    DeleteBehavior
    0.59
     endwhile
    0.56
     ImportError
    0.53
     totiž
    0.52
    ьаж
    0.52
    GEBURTSDATUM
    0.51
    writeFieldEnd
    0.50
     newBuilder
    0.49
    ngdoc
    0.49
     noDo
    0.48
    Act Density 0.320%

    No Known Activations