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

    Neuronpedia

    INDEX
    Explanations

    phrases related to cutting or being cut

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Moder
    -0.70
    BUS
    -0.68
    Registered
    -0.63
     compr
    -0.62
    Purchase
    -0.62
    SPONSORED
    -0.62
     Principal
    -0.60
     Kamp
    -0.60
     Boom
    -0.59
     Hur
    -0.58
    POSITIVE LOGITS
    scene
    1.69
    scenes
    1.58
    thro
    1.51
    aneous
    1.50
    lass
    1.41
    lasses
    1.39
    eness
    1.28
    away
    1.26
    aways
    1.23
    ters
    1.17
    Act Density 0.051%

    No Known Activations