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

    Neuronpedia

    INDEX
    Explanations

    Capital letter "U" followed by a single-digit number

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter 'U' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Noir
    -0.77
     flares
    -0.71
     Payton
    -0.69
    aline
    -0.65
     Emin
    -0.65
    ragon
    -0.64
     responsive
    -0.62
     Attribution
    -0.60
     aval
    -0.60
     dwarves
    -0.60
    POSITIVE LOGITS
    BLIC
    1.03
    NA
    1.02
    PLIC
    1.02
    PDATED
    1.01
    MA
    1.00
    WT
    0.98
    CLA
    0.96
    YA
    0.96
    BA
    0.95
    KE
    0.95
    Act Density 0.039%

    No Known Activations