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

    Neuronpedia

    INDEX
    Explanations

    single capitalized words or abbreviations in the middle of sequences

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical or statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mechdragon
    -0.78
    iton
    -0.75
    emonic
    -0.73
    Ĥ¬
    -0.71
     Binary
    -0.70
     Stellar
    -0.61
    omics
    -0.60
    BLIC
    -0.60
     veter
    -0.60
    EStream
    -0.59
    POSITIVE LOGITS
     ',
    0.96
    pictured
    0.69
     '.
    0.69
     '[
    0.69
    '."
    0.67
    ',
    0.65
    azel
    0.65
    ',"
    0.64
    yre
    0.64
    England
    0.64
    Act Density 0.088%

    No Known Activations