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

    Neuronpedia

    INDEX
    Explanations

    phrases related to evaluation or judgment

    oai_token-act-pair · gpt-3.5-turbo

    strong affirmations or statements of opinion in quotes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aired
    -0.77
    ///
    -0.73
    ayn
    -0.71
    ./
    -0.66
     Later
    -0.64
    ¯
    -0.61
     Houses
    -0.60
    }.
    -0.59
    —"
    -0.58
     Seasons
    -0.57
    POSITIVE LOGITS
     unequiv
    1.00
     absolutely
    0.98
     fundamentally
    0.95
     unequivocally
    0.93
     extraordinarily
    0.92
     certainly
    0.91
     definitely
    0.91
     unprecedented
    0.90
     tremendously
    0.89
     deeply
    0.88
    Act Density 0.459%

    No Known Activations