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

    Neuronpedia

    INDEX
    Explanations

    phrases related to unexpected consequences or surprising outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    possibility or likelihood

    np_acts-logits-general · gemini-2.0-flash

    conceivable or surprising events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.67
    nologue
    -0.63
     invokingState
    -0.57
    ẩm
    -0.57
     Efq
    -0.57
    UnitTesting
    -0.56
     chofe
    -0.56
    __':
    -0.54
    MessageTagHelper
    -0.54
    toise
    -0.53
    POSITIVE LOGITS
     durchaus
    0.80
     вполне
    0.71
     occasionally
    0.66
     behoort
    0.66
     fácilmente
    0.63
     zdar
    0.61
     ibland
    0.61
     conceivable
    0.60
     plausible
    0.60
     possibilité
    0.60
    Act Density 0.363%

    No Known Activations