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

    Neuronpedia

    INDEX
    Explanations

    infinitive verbs and their associated structures in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -1.14
     Monfieur
    -1.06
     scolaires
    -1.01
     againſt
    -0.99
     ainfi
    -0.94
     houſe
    -0.93
     myſelf
    -0.93
     ſeveral
    -0.90
     purpoſe
    -0.89
     becauſe
    -0.87
    POSITIVE LOGITS
     be
    0.94
     come
    0.78
     autorytatywna
    0.77
     become
    0.74
     “
    0.73
     ‘
    0.63
    ’
    0.60
    thenReturn
    0.59
     have
    0.58
    ValueStyle
    0.56
    Act Density 0.135%

    No Known Activations