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

    Neuronpedia

    INDEX
    Explanations

    references to physical human bodies

    oai_token-act-pair · gpt-3.5-turbo

    references to bodies, particularly in a context related to victims or remains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hoover
    -0.80
    BILITY
    -0.71
    é¾į
    -0.70
     Channel
    -0.67
     Liberty
    -0.66
    Americ
    -0.64
    UGE
    -0.64
    Mega
    -0.63
    BF
    -0.63
     Cobb
    -0.62
    POSITIVE LOGITS
     bodies
    1.08
    anguage
    1.07
    guards
    1.02
    hops
    0.98
    builders
    0.90
    tones
    0.90
    wagen
    0.89
     nodd
    0.87
    rats
    0.86
    ngth
    0.86
    Act Density 0.007%

    No Known Activations