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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal cases and investigations

    oai_token-act-pair · gpt-3.5-turbo

    recurring conjunctions and prepositions indicating relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     constitu
    -0.79
    assetsadobe
    -0.77
    PLA
    -0.73
    ategory
    -0.73
     ende
    -0.71
    etheless
    -0.69
     exting
    -0.68
     tremend
    -0.68
     awa
    -0.67
    Ô
    -0.66
    POSITIVE LOGITS
    rian
    0.67
    esley
    0.64
    ner
    0.59
    horn
    0.59
    bury
    0.59
    agar
    0.58
    gewater
    0.57
    nder
    0.56
    hot
    0.56
    eous
    0.56
    Act Density 0.242%

    No Known Activations