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

    Neuronpedia

    INDEX
    Explanations

    instances of the word 'or' and other terms indicating options or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.58
     contrário
    -0.54
    Autoritní
    -0.54
    Hentet
    -0.52
    ectady
    -0.51
     HasFactory
    -0.50
    tagHelperRunner
    -0.48
    principalTable
    -0.48
    出版年
    -0.48
     AttributeSet
    -0.48
    POSITIVE LOGITS
     possibly
    0.65
     preferably
    0.64
     sometimes
    0.64
     fewer
    0.63
     maybe
    0.60
     occasionally
    0.59
     ideally
    0.58
     voire
    0.56
     thậm
    0.54
    possibly
    0.53
    Act Density 0.385%

    No Known Activations