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

    Neuronpedia

    INDEX
    Explanations

    adjectives and verbs indicating increase or growth

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating degrees of intensity or escalation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    liest
    -0.80
     Flavoring
    -0.79
    glers
    -0.74
    cius
    -0.72
    arton
    -0.72
    pta
    -0.71
     Estimates
    -0.71
    ibling
    -0.70
    76561
    -0.70
    idth
    -0.69
    POSITIVE LOGITS
     uncomfortable
    1.08
     attractive
    1.02
     comfortable
    1.01
     cozy
    0.96
     uneasy
    0.95
     awkward
    0.94
     annoying
    0.94
     interesting
    0.94
     urgent
    0.93
     embarrassing
    0.92
    Act Density 0.283%

    No Known Activations