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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a variety of items or concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing abundance or excess

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onen
    -0.70
    imilar
    -0.69
    APTER
    -0.67
    FML
    -0.65
    yles
    -0.65
    witz
    -0.64
    ":"/
    -0.61
    akings
    -0.61
     <@
    -0.61
    ICAN
    -0.59
    POSITIVE LOGITS
     assorted
    0.95
    cellaneous
    0.79
    etc
    0.74
     downright
    0.70
     importantly
    0.70
     challeng
    0.69
    ĪĴ
    0.67
    ¥ŀ
    0.67
     general
    0.65
     finally
    0.64
    Act Density 0.395%

    No Known Activations