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

    Neuronpedia

    INDEX
    Explanations

    phrases related to initiating actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hed
    -0.14
     TORT
    -0.14
    ths
    -0.14
    cki
    -0.14
     tort
    -0.14
    iap
    -0.14
    azen
    -0.14
    enne
    -0.14
    indsight
    -0.13
    hea
    -0.13
    POSITIVE LOGITS
     kicked
    0.23
    boxing
    0.22
     Kick
    0.21
     kick
    0.20
     kicking
    0.19
    Kick
    0.18
    starter
    0.17
    kick
    0.17
     kicks
    0.17
    start
    0.17
    Act Density 0.014%

    No Known Activations