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

    Neuronpedia

    INDEX
    Explanations

    personal feelings and emotions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Camer
    -0.73
    adish
    -0.66
     Prospect
    -0.63
    photos
    -0.63
     Display
    -0.61
    esan
    -0.60
     Lies
    -0.60
     Tactics
    -0.59
     Accounting
    -0.59
    angle
    -0.58
    POSITIVE LOGITS
     comfortable
    1.09
     uneasy
    1.06
     compelled
    1.05
     vibrations
    0.94
     uncomfortable
    0.94
     obligated
    0.93
     confident
    0.92
     strongly
    0.88
     discomfort
    0.86
     acutely
    0.86
    Act Density 1.207%

    No Known Activations