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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "of" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.85
     itſelf
    -0.78
     houſe
    -0.78
     cauſe
    -0.77
     Houſe
    -0.76
     Efq
    -0.76
     purpoſe
    -0.74
     poffe
    -0.73
     RSSSF
    -0.72
     fevere
    -0.71
    POSITIVE LOGITS
     these
    0.91
     those
    0.90
     the
    0.79
     our
    0.72
     us
    0.67
     their
    0.63
     them
    0.63
     his
    0.63
     its
    0.63
     seus
    0.58
    Act Density 0.173%

    No Known Activations