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

    Neuronpedia

    INDEX
    Explanations

    expressions related to satisfaction or contentment with something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of satisfaction or happiness regarding various subjects or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -1.11
    uay
    -0.77
    nsics
    -0.74
    isSpecialOrderable
    -0.73
     beware
    -0.73
    fman
    -0.72
    ãĥ´ãĤ¡
    -0.70
    ciplinary
    -0.70
    angs
    -0.66
     eleph
    -0.66
    POSITIVE LOGITS
     outcome
    0.87
    clus
    0.70
     assurances
    0.70
    awed
    0.68
     outcomes
    0.67
    inement
    0.66
     len
    0.64
     unres
    0.63
     progress
    0.62
     success
    0.61
    Act Density 0.129%

    No Known Activations