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

    Neuronpedia

    INDEX
    Explanations

    proper nouns containing the sequence "u" followed by a single-digit number

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'u' in varying frequencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     horizont
    -0.77
    =-=-
    -0.70
     Attribution
    -0.69
     therap
    -0.67
    20439
    -0.66
     Payton
    -0.66
     initials
    -0.65
     Cosponsors
    -0.63
     CBI
    -0.63
     constants
    -0.62
    POSITIVE LOGITS
    pport
    1.29
    cca
    1.27
    ccess
    1.15
    pta
    1.09
    itton
    1.05
    cius
    1.05
    pling
    1.03
    seless
    1.02
    hiro
    1.02
    isine
    1.01
    Act Density 0.045%

    No Known Activations