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

    Neuronpedia

    INDEX
    Explanations

    adjectives expressing confusion, frustration, or uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    emotional responses related to confusion or frustration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     waivers
    -0.66
     bye
    -0.64
     deviations
    -0.63
     GP
    -0.62
    llan
    -0.59
     Policies
    -0.58
     approved
    -0.57
    payers
    -0.57
    eatures
    -0.57
     rule
    -0.57
    POSITIVE LOGITS
    ingly
    1.60
    ating
    0.99
    eful
    0.98
    ening
    0.96
    ifying
    0.92
    enment
    0.89
    ruciating
    0.89
    ing
    0.88
    risome
    0.86
    esc
    0.85
    Act Density 0.084%

    No Known Activations