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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating determination and resilience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     casts
    -0.14
    opsis
    -0.14
    tron
    -0.14
    odka
    -0.13
     batting
    -0.13
    件
    -0.13
    è±
    -0.13
    å²Ĺ
    -0.13
    çĽ
    -0.13
    éĻ
    -0.13
    POSITIVE LOGITS
    Styles
    0.21
     training
    0.19
     fight
    0.19
     KO
    0.18
     spar
    0.18
     Tyson
    0.18
     box
    0.18
     Styles
    0.17
     fighters
    0.17
     Training
    0.17
    Act Density 0.006%

    No Known Activations