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

    Neuronpedia

    INDEX
    Explanations

    mentions of wars or conflicts in a country

    oai_token-act-pair · gpt-3.5-turbo

    sentences that indicate completion or finality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yssey
    -0.72
    ascus
    -0.68
    »Ĵ
    -0.64
     spoiler
    -0.64
    thia
    -0.63
     rept
    -0.60
     referenced
    -0.59
    istar
    -0.59
     paraph
    -0.59
    ista
    -0.59
    POSITIVE LOGITS
     They
    1.31
     Their
    1.19
     Those
    1.11
     Often
    1.10
     Sometimes
    1.08
     These
    1.06
     However
    1.05
     Others
    1.04
     Each
    1.04
     Some
    0.99
    Act Density 0.610%

    No Known Activations