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

    Neuronpedia

    INDEX
    Explanations

    mentions of a boss, especially in workplace contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "boss."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Scotia
    -0.85
    aval
    -0.71
     Pwr
    -0.69
    opter
    -0.67
    lihood
    -0.67
    ibaba
    -0.67
     Trails
    -0.66
    agra
    -0.66
    ISS
    -0.65
    issance
    -0.65
    POSITIVE LOGITS
    boss
    0.81
    ccoli
    0.75
    pins
    0.74
    nuts
    0.71
     watering
    0.71
    berman
    0.71
    ulas
    0.70
    pin
    0.69
    umo
    0.69
    anova
    0.69
    Act Density 0.010%

    No Known Activations