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

    Neuronpedia

    INDEX
    Explanations

    infinitive verbs indicating actions or intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -1.22
     Monfieur
    -1.10
     againſt
    -1.03
     ainfi
    -0.98
     scolaires
    -0.97
     becauſe
    -0.97
     myſelf
    -0.95
     sauvages
    -0.94
     itſelf
    -0.94
     themſelves
    -0.92
    POSITIVE LOGITS
     be
    0.93
     “
    0.80
     become
    0.79
     ‘
    0.66
    ’
    0.66
     have
    0.65
     do
    0.65
     come
    0.64
     
    0.61
     can
    0.60
    Act Density 0.127%

    No Known Activations