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

    Neuronpedia

    INDEX
    Explanations

    phrases related to law, investigations, and official events

    oai_token-act-pair · gpt-3.5-turbo

    elements related to conflict or disagreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     domest
    -0.51
    bred
    -0.47
    adena
    -0.43
     artisan
    -0.43
    animate
    -0.42
    packed
    -0.42
     miniature
    -0.41
     vegetarian
    -0.41
     Sty
    -0.41
    liter
    -0.41
    POSITIVE LOGITS
    ãģ®é
    0.55
     explan
    0.52
    ij士
    0.51
    upon
    0.51
     paraph
    0.51
     inconsistencies
    0.51
     implying
    0.50
     reiterate
    0.50
     inconsistency
    0.50
    Comment
    0.50
    Act Density 2.029%

    No Known Activations