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

    Neuronpedia

    INDEX
    Explanations

    references to hand-to-hand combat

    oai_token-act-pair · gpt-3.5-turbo

    terms related to combat or fighting scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oint
    -0.87
    icket
    -0.85
    andan
    -0.84
    anke
    -0.80
    oos
    -0.80
    oof
    -0.80
    ais
    -0.80
    lessly
    -0.80
    anda
    -0.79
    andise
    -0.77
    POSITIVE LOGITS
     Mae
    0.64
     prevail
    0.61
     steady
    0.60
    Combat
    0.60
     torches
    0.59
    DEN
    0.59
    jah
    0.58
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    0.58
    bane
    0.57
     legion
    0.57
    Act Density 0.036%

    No Known Activations