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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by a verb in the past tense

    oai_token-act-pair · gpt-3.5-turbo

    significant conjunctions and prepositions that indicate relationships or connections between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     SAN
    -0.71
     EFF
    -0.71
     distingu
    -0.70
     ESP
    -0.69
     ����
    -0.68
    assetsadobe
    -0.67
     DeL
    -0.66
     jun
    -0.66
     colle
    -0.65
     hurd
    -0.65
    POSITIVE LOGITS
    gas
    1.00
    zon
    0.99
    roth
    0.99
    raq
    0.98
    fur
    0.96
    yx
    0.93
    yl
    0.93
    exc
    0.93
    gar
    0.91
    oxic
    0.90
    Act Density 0.352%

    No Known Activations