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

    Neuronpedia

    INDEX
    Explanations

    references to physical confrontations or battles

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "fight" in the context of conflict or struggle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Seym
    -0.75
    uliffe
    -0.74
    etheless
    -0.70
    ixel
    -0.70
    ummer
    -0.68
    asper
    -0.65
    operated
    -0.64
    Software
    -0.64
    anol
    -0.64
    IELD
    -0.63
    POSITIVE LOGITS
    fight
    1.20
     fight
    1.07
     fights
    1.05
    fights
    1.03
     Fight
    1.00
    fighters
    0.93
    fighting
    0.91
     FIGHT
    0.90
     fought
    0.87
     spar
    0.85
    Act Density 0.020%

    No Known Activations