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

    Neuronpedia

    INDEX
    Explanations

    words indicating negative or controversial situations

    oai_token-act-pair · gpt-3.5-turbo

    interruptions or ellipses in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icum
    -0.81
    rir
    -0.73
    rons
    -0.71
    oit
    -0.71
     purse
    -0.70
    wagen
    -0.70
    fen
    -0.70
     bod
    -0.69
    anqu
    -0.68
    terday
    -0.67
    POSITIVE LOGITS
     Written
    1.03
     Appears
    1.01
    BUT
    0.97
     Continued
    0.85
     ...
    0.83
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.83
     WATCHED
    0.81
     âĢİ
    0.80
    Marginal
    0.80
    CBC
    0.78
    Act Density 0.008%

    No Known Activations