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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing an unexpected or surprising outcome

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :✨
    -0.48
    sche
    -0.44
    спек
    -0.44
    idation
    -0.43
    flashdata
    -0.42
     love
    -0.42
    みな
    -0.41
     HOR
    -0.41
    琴
    -0.41
    éges
    -0.41
    POSITIVE LOGITS
    prisingly
    1.09
     виправивши
    1.06
     coincidence
    0.78
     Pourtant
    0.73
    lillah
    0.72
    Сюжет
    0.71
    følgelig
    0.71
    ureusement
    0.70
     Seeder
    0.70
     препратки
    0.70
    Act Density 0.293%

    No Known Activations