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

    Neuronpedia

    INDEX
    Explanations

    names of specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and their associated actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ataka
    -0.71
    ipedia
    -0.68
    umbers
    -0.68
    onto
    -0.67
    uminium
    -0.65
    enegger
    -0.62
    ould
    -0.62
    isure
    -0.61
    ickr
    -0.61
    gorithm
    -0.61
    POSITIVE LOGITS
     She
    0.79
     Quan
    0.78
     Born
    0.77
     Vent
    0.72
     Bott
    0.71
     Gou
    0.71
     Moor
    0.71
     Pt
    0.71
     Flav
    0.70
     Schwarz
    0.70
    Act Density 1.392%

    No Known Activations