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

    Neuronpedia

    INDEX
    Explanations

    phrases containing technical terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation and their frequency in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¨ãĥ«
    -0.77
    èĢħ
    -0.75
    erenn
    -0.71
    iku
    -0.69
    abama
    -0.69
    ROR
    -0.68
    Ö¼
    -0.67
    wash
    -0.66
    ãĤ¼ãĤ¦ãĤ¹
    -0.65
    ļéĨĴ
    -0.64
    POSITIVE LOGITS
     nevertheless
    1.16
     there
    1.01
     it
    0.95
     nonetheless
    0.93
    there
    0.89
     namely
    0.84
     they
    0.80
     neither
    0.78
     albeit
    0.77
     nobody
    0.73
    Act Density 0.176%

    No Known Activations