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

    Neuronpedia

    INDEX
    Explanations

    the letters "ID" followed by a single digit or the letter "R"

    oai_token-act-pair · gpt-3.5-turbo

    references to identification (ID) codes or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bilt
    -0.78
    theless
    -0.73
    cffff
    -0.68
     Silence
    -0.68
     silence
    -0.66
    iful
    -0.65
    phrine
    -0.64
    ctuary
    -0.64
    Ò
    -0.64
    acters
    -0.64
    POSITIVE LOGITS
    iots
    1.12
    entity
    1.07
    aho
    1.07
    DEN
    1.02
    irect
    1.02
    LER
    0.97
    ENT
    0.96
    ocument
    0.93
    iop
    0.92
    ictionary
    0.90
    Act Density 0.013%

    No Known Activations