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

    Neuronpedia

    INDEX
    Explanations

    words or phrases enclosed in quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    quotations or quotation marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ļ½
    -0.92
    ĻĤ
    -0.77
    ¿
    -0.76
    ¸
    -0.74
    ailing
    -0.73
    ¾
    -0.72
    ãĥ´
    -0.67
    oho
    -0.66
    ason
    -0.66
    stant
    -0.65
    POSITIVE LOGITS
    /"
    1.42
     moniker
    0.86
     aka
    0.73
     designation
    0.72
     ("
    0.70
     label
    0.68
     appell
    0.67
     motto
    0.66
    ModLoader
    0.65
    aneers
    0.63
    Act Density 0.109%

    No Known Activations