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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "fight," especially in various contexts suggesting struggle or conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    帖最后由
    -0.81
    tonode
    -0.81
     généraux
    -0.76
    */].
    -0.75
     ErrIntOverflow
    -0.75
     kasarigan
    -0.73
    PLY
    -0.71
    `}
    -0.71
     conséquence
    -0.71
    theless
    -0.70
    POSITIVE LOGITS
     fight
    2.21
    fight
    2.15
     fights
    2.00
     Fight
    1.98
     FIGHT
    1.97
     fought
    1.94
     fighting
    1.91
     Fighting
    1.90
    fighting
    1.83
    Fight
    1.82
    Act Density 0.045%

    No Known Activations