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

    Neuronpedia

    INDEX
    Explanations

    phrases related to limitations or constraints

    oai_token-act-pair · gpt-3.5-turbo

    negative assertions or impossibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.77
     snipp
    -0.65
     Signs
    -0.64
    senal
    -0.63
     Seeds
    -0.62
    bats
    -0.60
    heavy
    -0.59
     Sparrow
    -0.59
    flame
    -0.58
    Sense
    -0.58
    POSITIVE LOGITS
     afford
    1.55
     tolerate
    1.15
     rely
    1.09
     conceive
    1.05
     condone
    1.03
     withstand
    1.01
     guarantee
    1.01
     abide
    1.00
     exclude
    0.98
     ignore
    0.98
    Act Density 0.054%

    No Known Activations