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

    Neuronpedia

    INDEX
    Explanations

    mentions and descriptions of different types of warriors throughout various contexts, including historical, mythological, and fictional

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    uate
    -0.85
    orage
    -0.79
    ories
    -0.79
    changes
    -0.75
    ions
    -0.74
    ibly
    -0.71
    upon
    -0.70
    ascript
    -0.69
    urations
    -0.68
    ĸļ
    -0.67
    POSITIVE LOGITS
    riors
    1.35
    rior
    1.33
    ¯¯¯¯
    0.94
    fare
    0.89
    ¯¯¯¯¯¯¯¯
    0.85
     warriors
    0.84
    ¯¯
    0.83
    hip
    0.82
     warrior
    0.81
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    0.77
    Act Density 0.062%

    No Known Activations