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

    Neuronpedia

    INDEX
    Explanations

    syntactical elements and control structures in code-like text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PreferredItem
    -0.98
     pleaſure
    -0.90
    principalColumn
    -0.88
     betweenstory
    -0.85
     Monfieur
    -0.84
     poffe
    -0.84
     oprot
    -0.83
    WindowConstants
    -0.81
    wieś
    -0.79
     ſeveral
    -0.79
    POSITIVE LOGITS
    if
    0.59
     if
    0.56
    {%
    0.56
    czek
    0.53
    ="<?=
    0.49
    erais
    0.49
    %
    0.48
    <?
    0.47
     Vor
    0.47
    立
    0.47
    Act Density 0.082%

    No Known Activations