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

    Neuronpedia

    INDEX
    Explanations

    words related to physical punishment or discipline

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "spank" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    λ
    -0.69
     Loft
    -0.64
     Deng
    -0.63
     redistributed
    -0.61
     Lancet
    -0.61
     Fem
    -0.61
     defective
    -0.61
    glass
    -0.61
    Interstitial
    -0.59
     emitted
    -0.59
    POSITIVE LOGITS
    anked
    1.04
    ertodd
    0.99
    anking
    0.93
    anks
    0.86
    ety
    0.85
    ushima
    0.82
    haw
    0.79
    ersen
    0.78
    ased
    0.76
    abase
    0.76
    Act Density 0.005%

    No Known Activations