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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "of" occurring in text

    oai_token-act-pair · gpt-3.5-turbo

    references to systematic reviews and analyses of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oult
    -0.65
    igue
    -0.63
    ulo
    -0.61
     trem
    -0.61
    ring
    -0.61
    cil
    -0.60
    âĹ¼
    -0.58
    Thumbnail
    -0.58
    ription
    -0.58
    eral
    -0.58
    POSITIVE LOGITS
     sorts
    0.79
     course
    0.74
     literature
    0.68
     existing
    0.68
     the
    0.68
     behalf
    0.66
     these
    0.66
    Ĭ±
    0.66
    articles
    0.65
     grievances
    0.63
    Act Density 0.157%

    No Known Activations