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

    Neuronpedia

    INDEX
    Explanations

    numerical ranges or quantities mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to ranges and numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Voices
    -0.74
    043
    -0.64
     Duo
    -0.62
     457
    -0.61
     Donovan
    -0.61
     Gutenberg
    -0.61
     Ki
    -0.61
     Garner
    -0.60
     Pryor
    -0.60
    yss
    -0.60
    POSITIVE LOGITS
    isma
    0.72
    0.70
    cffff
    0.68
    10
    0.68
    8
    0.67
    iron
    0.66
    8000
    0.65
    dam
    0.65
    adden
    0.65
    ocene
    0.63
    Act Density 0.078%

    No Known Activations