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

    Neuronpedia

    INDEX
    Explanations

    exclamations and commands with strong emotional intensity

    oai_token-act-pair · gpt-3.5-turbo

    exclamatory interjections or expressions of strong emotion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.93
     dispers
    -0.68
    ividual
    -0.67
     scatter
    -0.67
     misunder
    -0.67
     smokes
    -0.66
     recogn
    -0.66
     scattering
    -0.65
     segreg
    -0.65
     monop
    -0.64
    POSITIVE LOGITS
    ¬
    1.32
    ľ
    1.24
    ¦
    1.23
    ª
    1.21
    º
    1.17
    £
    1.16
    ł
    1.15
    ¡
    1.13
    İ
    1.08
    §
    1.07
    Act Density 0.185%

    No Known Activations