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

    Neuronpedia

    INDEX
    Explanations

    patterns related to pricing or cost information

    oai_token-act-pair · gpt-3.5-turbo

    fractional values related to pricing or subscriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ļéĨĴ
    -0.77
     Reconstruction
    -0.73
     Starr
    -0.71
     Edgar
    -0.67
     Pag
    -0.67
     pse
    -0.65
     Kern
    -0.65
     Flowers
    -0.64
     Tornado
    -0.63
     Syl
    -0.63
    POSITIVE LOGITS
    etc
    0.95
    1000
    0.91
    each
    0.87
    dt
    0.87
    vol
    0.87
    power
    0.87
    hour
    0.86
    schild
    0.85
    paid
    0.84
    legal
    0.84
    Act Density 0.035%

    No Known Activations