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

    Neuronpedia

    INDEX
    Explanations

    notations about various famous individuals and their achievements or actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    uta
    -0.78
    rency
    -0.69
    VO
    -0.67
    ¥µ
    -0.66
    voy
    -0.65
    compan
    -0.65
    parts
    -0.64
    uin
    -0.63
    oco
    -0.62
    perty
    -0.62
    POSITIVE LOGITS
     undergo
    0.86
     underwent
    0.83
     graduated
    0.76
     founded
    0.75
     earns
    0.75
     admits
    0.73
     hailed
    0.72
     credited
    0.72
     flanked
    0.72
     nicknamed
    0.72
    Act Density 0.158%

    No Known Activations