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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate chance or occurrence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alink
    -0.19
    amburg
    -0.15
    pg
    -0.15
    rnd
    -0.14
    attles
    -0.14
     hele
    -0.14
    inho
    -0.14
    piring
    -0.14
    py
    -0.14
    imming
    -0.14
    POSITIVE LOGITS
     coinc
    0.23
    stance
    0.21
    STANCE
    0.20
    лев
    0.18
    ily
    0.18
    stances
    0.17
    fortunate
    0.16
    Upon
    0.16
    auer
    0.16
     Upon
    0.16
    Act Density 0.010%

    No Known Activations