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

    Neuronpedia

    INDEX
    Explanations

    names of specific people and their roles or associations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    TYPE
    -0.71
    DATA
    -0.70
    à¤
    -0.69
    rection
    -0.66
    sole
    -0.66
    à¨
    -0.64
    Enh
    -0.64
    Bind
    -0.64
    Effective
    -0.63
    ASED
    -0.63
    POSITIVE LOGITS
    hips
    1.35
    hip
    1.19
    paces
    1.01
     alike
    0.98
     ranging
    0.86
    hots
    0.85
     Cheryl
    0.84
     including
    0.83
    folk
    0.81
     who
    0.80
    Act Density 0.559%

    No Known Activations