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

    Neuronpedia

    INDEX
    Explanations

    words or phrases indicating personal thoughts, opinions, or emotions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal feelings or emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umbn
    -0.68
    adish
    -0.62
    andise
    -0.62
    fig
    -0.61
    ciating
    -0.61
    esan
    -0.59
    enta
    -0.59
    oys
    -0.59
    etting
    -0.58
    uning
    -0.58
    POSITIVE LOGITS
     compelled
    1.23
     comfortable
    1.16
     obligated
    1.10
     uneasy
    1.10
     strongly
    1.08
     confident
    1.08
     obliged
    1.01
     betrayed
    1.00
     passionately
    1.00
     ashamed
    0.96
    Act Density 0.043%

    No Known Activations