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

    Neuronpedia

    INDEX
    Explanations

    words related to places or people's names

    oai_token-act-pair · gpt-3.5-turbo

    specific combinations of vowels and syllabic patterns in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    INAL
    -0.87
    PDATE
    -0.77
    ãĥ¯ãĥ³
    -0.72
    actionDate
    -0.71
    ãĤ©
    -0.68
    ADRA
    -0.66
    ¬
    -0.66
    AUD
    -0.65
    ãĥ©ãĥ³
    -0.64
    isSpecialOrderable
    -0.64
    POSITIVE LOGITS
    phia
    0.82
     Gardens
    0.77
    wu
    0.77
     Tribe
    0.74
    ionage
    0.72
    etus
    0.72
    ttes
    0.70
     Farms
    0.69
    velt
    0.68
    ghan
    0.67
    Act Density 0.276%

    No Known Activations