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

    Neuronpedia

    INDEX
    Explanations

    words related to subjective emotions such as feelings and sentiments expressed by individuals

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ciating
    -0.78
    esan
    -0.69
    adish
    -0.68
    agh
    -0.67
    ãĥīãĥ©
    -0.65
    mination
    -0.65
    ades
    -0.65
    fig
    -0.64
    enta
    -0.64
    arb
    -0.63
    POSITIVE LOGITS
     compelled
    1.41
     obligated
    1.29
     uneasy
    1.23
     comfortable
    1.21
     confident
    1.19
     obliged
    1.19
     betrayed
    1.18
     ashamed
    1.17
     uncomfortable
    1.13
     sorry
    1.10
    Act Density 0.049%

    No Known Activations