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

    Neuronpedia

    INDEX
    Explanations

    symbols used in formatting or separating elements in text

    oai_token-act-pair · gpt-3.5-turbo

    quotation marks and symbols indicating video or media references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bably
    -0.83
    oresc
    -0.78
    nuts
    -0.76
    itably
    -0.76
    itionally
    -0.75
    orical
    -0.74
    anmar
    -0.73
    orically
    -0.72
    ania
    -0.71
    orial
    -0.69
    POSITIVE LOGITS
    »
    1.03
     »
    0.87
     âĢº
    0.79
     «
    0.76
    ETS
    0.69
    âĸº
    0.67
    Sov
    0.66
    âĢ¢âĢ¢
    0.66
     Flickr
    0.65
    LINE
    0.65
    Act Density 0.011%

    No Known Activations