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

    Neuronpedia

    INDEX
    Explanations

    specific names and phrases related to politics or current affairs

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, groups, or entities, particularly in a sociopolitical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dule
    -0.66
    otonin
    -0.65
    umbn
    -0.65
    iculty
    -0.65
    âĸ¬âĸ¬
    -0.61
    igm
    -0.61
    ():
    -0.59
    iatus
    -0.58
    âĿ
    -0.58
    verages
    -0.57
    POSITIVE LOGITS
     notwithstanding
    1.60
     preferring
    0.97
     included
    0.95
     said
    0.89
     permitting
    0.84
     being
    0.83
     argues
    0.79
     says
    0.76
     assures
    0.75
     explains
    0.72
    Act Density 0.633%

    No Known Activations