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

    Neuronpedia

    INDEX
    Explanations

    expressions of hope or anticipation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of hope and encouragement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esp
    -0.69
     (âĪĴ
    -0.66
    note
    -0.66
    typically
    -0.65
    minus
    -0.62
    Marx
    -0.61
    imilar
    -0.61
    ume
    -0.60
    ELD
    -0.60
     ¶
    -0.58
    POSITIVE LOGITS
     someday
    1.33
     tomorrow
    0.73
     Readers
    0.69
     readers
    0.67
     dissu
    0.64
     recons
    0.64
     outcome
    0.63
    bably
    0.63
     future
    0.62
     patience
    0.62
    Act Density 0.201%

    No Known Activations