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

    Neuronpedia

    INDEX
    Explanations

    phrases related to job titles and positions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     surgeons
    -0.67
    rums
    -0.64
     stret
    -0.64
    Attach
    -0.63
     idiots
    -0.61
     needles
    -0.61
     therapists
    -0.60
     unbeliev
    -0.59
    Duration
    -0.59
     fools
    -0.58
    POSITIVE LOGITS
     emer
    1.13
     extraord
    0.81
     overseeing
    0.79
    utive
    0.77
     Emer
    0.75
    itatively
    0.75
    director
    0.74
    hesis
    0.71
     of
    0.70
    wark
    0.67
    Act Density 0.592%

    No Known Activations