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

    Neuronpedia

    INDEX
    Explanations

    words related to physical combat or disputes

    oai_token-act-pair · gpt-3.5-turbo

    references to physical confrontations or disputes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Arch
    -0.67
     Mellon
    -0.65
     query
    -0.63
     indicating
    -0.63
    SS
    -0.63
     infer
    -0.62
     constituted
    -0.62
    sample
    -0.61
     tuber
    -0.61
     indicative
    -0.60
    POSITIVE LOGITS
     fights
    3.81
    fights
    2.94
     battles
    2.27
     fight
    2.26
    fight
    2.17
     Fight
    1.79
    Fight
    1.68
     fighting
    1.67
    fighting
    1.63
     FIGHT
    1.63
    Act Density 0.010%

    No Known Activations