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

    Neuronpedia

    INDEX
    Explanations

    prepositions that indicate relationships or connections within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſtate
    -1.05
     myſelf
    -1.05
     itſelf
    -0.99
     uſe
    -0.97
     pleaſure
    -0.96
     houſe
    -0.92
     purpoſe
    -0.90
     raiſ
    -0.87
     Houſe
    -0.87
     poffe
    -0.87
    POSITIVE LOGITS
     the
    1.20
     a
    1.03
     an
    0.90
     “
    0.79
     both
    0.71
     numerous
    0.67
     several
    0.66
    :
    0.65
     either
    0.64
     all
    0.61
    Act Density 1.375%

    No Known Activations