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

    Neuronpedia

    INDEX
    Explanations

    instances where a particular name or term "u" is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the letter 'u' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     horizont
    -0.78
    =-=-
    -0.77
     Attribution
    -0.68
     Payton
    -0.67
     skelet
    -0.67
     therap
    -0.66
    20439
    -0.63
    */(
    -0.61
     CBI
    -0.61
     Cosponsors
    -0.61
    POSITIVE LOGITS
    cca
    1.32
    pport
    1.21
    ccess
    1.13
    pta
    1.05
    cius
    1.04
    seless
    1.04
    hiro
    1.01
    itton
    1.00
    endo
    0.98
    ña
    0.96
    Act Density 0.060%

    No Known Activations