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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences discussing probabilities or likelihoods

    oai_token-act-pair · gpt-3.5-turbo

    statistical terms related to odds and probability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emark
    -0.68
     accomp
    -0.66
    issance
    -0.65
    este
    -0.65
    Ô
    -0.64
    iners
    -0.64
    exempt
    -0.64
     ensu
    -0.64
     awa
    -0.63
    ined
    -0.63
    POSITIVE LOGITS
    llor
    1.13
     ratio
    0.84
    cale
    0.83
     ratios
    0.78
    laus
    0.72
     stacked
    0.70
     Ratio
    0.68
     of
    0.67
    liest
    0.66
     density
    0.65
    Act Density 0.051%

    No Known Activations