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

    Neuronpedia

    INDEX
    Explanations

    names of individuals with numerical values attached

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    naissance
    -0.81
    interrupted
    -0.81
    forcing
    -0.77
    ĸļ
    -0.76
    ©¶æ¥µ
    -0.75
    roud
    -0.72
    oop
    -0.70
    forcement
    -0.69
    ipation
    -0.67
    angible
    -0.66
    POSITIVE LOGITS
     wisely
    0.98
     Cosponsors
    0.92
     randomly
    0.90
     chosen
    0.89
     finalists
    0.79
     preset
    0.76
     preferred
    0.74
     preference
    0.74
     nomination
    0.73
     option
    0.73
    Act Density 0.232%

    No Known Activations