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

    Neuronpedia

    INDEX
    Explanations

    the word "boss" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to "boss" or leadership roles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Scotia
    -0.84
     Pwr
    -0.70
     Trails
    -0.68
     CTR
    -0.66
     Lauder
    -0.66
    selves
    -0.64
    ctica
    -0.63
     Democr
    -0.61
    Balt
    -0.61
     Glob
    -0.60
    POSITIVE LOGITS
    hips
    0.87
    anova
    0.87
    xon
    0.87
    es
    0.86
    nuts
    0.86
    olean
    0.86
    ulas
    0.85
    umo
    0.84
    nut
    0.82
    boss
    0.80
    Act Density 0.032%

    No Known Activations