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

    Neuronpedia

    INDEX
    Explanations

    words related to physical altercation or conflict

    oai_token-act-pair · gpt-3.5-turbo

    references to conflicts and physical altercations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    engineering
    -0.77
    ogo
    -0.77
     stocking
    -0.67
    Label
    -0.67
    ãģĹ
    -0.67
    aks
    -0.66
    label
    -0.65
    ige
    -0.65
    serving
    -0.65
    Cover
    -0.65
    POSITIVE LOGITS
    halla
    1.08
     ensued
    1.02
     between
    0.99
     brawl
    0.92
     raged
    0.89
     raging
    0.86
     banter
    0.84
    SHIP
    0.83
     against
    0.81
     Royale
    0.81
    Act Density 0.165%

    No Known Activations