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

    Neuronpedia

    INDEX
    Explanations

    political terms and actions

    oai_token-act-pair · gpt-3.5-turbo

    political terms and phrases related to elections and social issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Variant
    -0.73
    earchers
    -0.70
    ocation
    -0.64
    undrum
    -0.64
    taboola
    -0.63
    uala
    -0.60
     misunder
    -0.59
     fragmentation
    -0.59
     Differences
    -0.58
    unity
    -0.58
    POSITIVE LOGITS
     supposedly
    0.98
     ostensibly
    0.91
     already
    0.89
     theirs
    0.86
     otherwise
    0.83
     blatantly
    0.82
     expressly
    0.80
     actually
    0.80
     admittedly
    0.79
     arguably
    0.79
    Act Density 0.928%

    No Known Activations