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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically locations or organizations with a focus on New York (N.Y.) and luxury-related terms

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'Y' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ities
    -0.85
    ciating
    -0.81
    itures
    -0.78
    entimes
    -0.77
    icable
    -0.73
    ãĥ¼ãĥĨãĤ£
    -0.73
    icably
    -0.71
    byter
    -0.68
    oise
    -0.66
    iture
    -0.66
    POSITIVE LOGITS
    STEM
    1.12
    ORK
    1.01
    PE
    1.00
    EAR
    0.99
    outube
    0.98
    ield
    0.96
    ANK
    0.94
    outh
    0.93
    ANG
    0.90
    OND
    0.90
    Act Density 0.034%

    No Known Activations