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

    Neuronpedia

    INDEX
    Explanations

    verbs related to an explosive or impactful event

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Ĥ¬
    -0.69
    grass
    -0.66
    SEA
    -0.64
    flix
    -0.62
    chal
    -0.61
    ¥µ
    -0.60
    boarding
    -0.57
     Warwick
    -0.54
    lda
    -0.54
    externalActionCode
    -0.54
    POSITIVE LOGITS
    osion
    1.21
    oded
    1.16
    icating
    1.11
    ausible
    1.08
    icates
    1.06
    icate
    1.03
    anting
    1.02
    oding
    1.00
    icit
    1.00
    ications
    0.95
    Act Density 8.767%

    No Known Activations