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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating extreme actions or comparisons

    oai_token-act-pair · gpt-3.5-turbo

    expressions of comparison or measures of extent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olitical
    -0.78
    olitics
    -0.77
    izons
    -0.72
    VERTISEMENT
    -0.68
    ocene
    -0.68
    ilial
    -0.67
    aceae
    -0.66
    ptoms
    -0.65
    awks
    -0.65
    lasses
    -0.64
    POSITIVE LOGITS
     committing
    1.45
     appointing
    1.43
     sending
    1.41
     executing
    1.40
     administering
    1.39
     stealing
    1.39
     initiating
    1.38
     constructing
    1.38
     murdering
    1.38
     placing
    1.38
    Act Density 0.763%

    No Known Activations