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

    Neuronpedia

    INDEX
    Explanations

    keywords related to specific individuals or places, likely proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Pul" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¤ãĥĪ
    -0.91
     Cassidy
    -0.73
    ãĢIJ
    -0.70
     Butterfly
    -0.68
     Organisation
    -0.67
    ele
    -0.66
     Leap
    -0.65
     Misty
    -0.64
    ELS
    -0.64
    ICLE
    -0.64
    POSITIVE LOGITS
    iple
    1.21
    monary
    1.17
    pees
    0.99
    gur
    0.97
    umin
    0.95
    rito
    0.88
    leted
    0.86
    inary
    0.86
    cery
    0.85
    cer
    0.84
    Act Density 0.041%

    No Known Activations