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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to locations along with a few medical terms

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and locations associated with "Nan."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    */(
    -0.75
    tto
    -0.72
     Jarrett
    -0.67
    é¾įå¥ij士
    -0.67
    anwhile
    -0.67
     mileage
    -0.66
    EEP
    -0.65
    âķIJâķIJ
    -0.64
    ATURES
    -0.63
    ãĤ¦
    -0.63
    POSITIVE LOGITS
     Nan
    1.14
    igans
    0.98
    ocry
    0.94
    omi
    0.85
    los
    0.83
     hous
    0.82
    omach
    0.82
    kees
    0.80
    aval
    0.80
    awan
    0.79
    Act Density 0.010%

    No Known Activations