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

    Neuronpedia

    INDEX
    Explanations

    words related to bosses or authority figures

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "boss" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Scotia
    -0.84
     Pwr
    -0.80
    ibaba
    -0.70
    lihood
    -0.69
    issance
    -0.69
     Trails
    -0.67
    Interstitial
    -0.67
     ILCS
    -0.66
     Flavoring
    -0.64
    FORMATION
    -0.62
    POSITIVE LOGITS
    anova
    0.80
    es
    0.76
    boss
    0.75
    enthal
    0.74
    erker
    0.73
    enhagen
    0.73
    nuts
    0.73
    hatt
    0.71
    nut
    0.71
    ulas
    0.70
    Act Density 0.033%

    No Known Activations