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

    Neuronpedia

    INDEX
    Explanations

    proper names or surnames

    oai_token-act-pair · gpt-3.5-turbo

    repeated sequences of letters or syllables in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     citation
    -0.60
     hers
    -0.60
     exceptions
    -0.59
    OLOGY
    -0.59
     exemptions
    -0.59
     exception
    -0.58
     arts
    -0.57
     duplication
    -0.56
     community
    -0.56
     regeneration
    -0.55
    POSITIVE LOGITS
    kaya
    1.69
    ky
    1.64
    ki
    1.64
    nyder
    1.46
    kie
    1.38
    ullivan
    1.29
    ka
    1.26
    hire
    1.21
    hip
    1.21
    mith
    1.20
    Act Density 0.149%

    No Known Activations