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

    Neuronpedia

    INDEX
    Explanations

    phrases related to important aspects or components

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.87
     Tsukuyomi
    -0.79
    ilk
    -0.76
    ibal
    -0.74
    renheit
    -0.72
     vomit
    -0.69
     Carbuncle
    -0.68
    uthor
    -0.68
    LV
    -0.68
    Ń·
    -0.67
    POSITIVE LOGITS
    stone
    1.12
     importance
    0.99
    stay
    0.99
     ingredient
    0.97
    stones
    0.92
     components
    0.91
     distinguishing
    0.90
     contributor
    0.90
     tenets
    0.89
     contributors
    0.89
    Act Density 4.041%

    No Known Activations