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

    Neuronpedia

    INDEX
    Explanations

    words indicating specific relationships or connections, such as "when", "and", and "by"

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and transition words indicating relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     photoc
    -0.68
    assetsadobe
    -0.66
     [];
    -0.66
     behav
    -0.64
     acron
    -0.63
     ESP
    -0.62
     SAN
    -0.62
     DeL
    -0.61
     horizont
    -0.61
     microphones
    -0.60
    POSITIVE LOGITS
    roth
    0.96
    raq
    0.96
    zon
    0.93
    mac
    0.92
    kin
    0.91
    yx
    0.88
    aris
    0.88
    roy
    0.87
    nard
    0.87
    fur
    0.86
    Act Density 0.340%

    No Known Activations