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

    Neuronpedia

    INDEX
    Explanations

    references to physical body features or modifications

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ablishment
    -0.72
    ĨĴ
    -0.71
    ostics
    -0.66
    eers
    -0.65
    ADRA
    -0.63
     Bulldogs
    -0.63
    hower
    -0.62
     Luk
    -0.62
    ablish
    -0.60
     prest
    -0.60
    POSITIVE LOGITS
    red
    1.13
    lets
    1.05
    ring
    1.04
    lett
    1.01
    crow
    0.97
    fed
    0.96
    let
    0.93
    abs
    0.93
    face
    0.93
    uler
    0.93
    Act Density 0.020%

    No Known Activations