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

    Neuronpedia

    INDEX
    Explanations

    phrases related to high stakes or potential consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the importance or significance of various matters at stake

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ript
    -0.75
    rounder
    -0.65
    bor
    -0.65
    orously
    -0.63
     Pratt
    -0.63
    chlor
    -0.63
     Bore
    -0.63
    omin
    -0.62
    ithe
    -0.62
     pat
    -0.60
    POSITIVE LOGITS
    FontSize
    0.75
    xus
    0.70
    TextColor
    0.69
    ulkan
    0.68
    dden
    0.67
    mma
    0.66
    ħĭ
    0.65
    uble
    0.65
     disposal
    0.63
     brink
    0.62
    Act Density 0.031%

    No Known Activations