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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing understanding or comprehension

    oai_token-act-pair · gpt-3.5-turbo

    expressions of understanding regarding various situations or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    astics
    -0.75
    thood
    -0.71
    thing
    -0.68
    etheus
    -0.67
    apons
    -0.64
    idav
    -0.62
    estial
    -0.61
    mage
    -0.61
    onson
    -0.60
    illac
    -0.60
    POSITIVE LOGITS
     why
    1.06
     frustration
    0.85
     frustrations
    0.77
     impat
    0.72
     needing
    0.72
     wanting
    0.71
     sympathy
    0.70
     sadness
    0.70
     criticism
    0.69
     grief
    0.69
    Act Density 0.106%

    No Known Activations