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

    Neuronpedia

    INDEX
    Explanations

    brackets and braces indicating sections of mathematical expressions or algorithms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    engkap
    -0.16
    ryn
    -0.15
    Jud
    -0.15
    GRES
    -0.14
    ynes
    -0.14
    iyah
    -0.14
    ék
    -0.14
    ABCDEFGHIJKLMNOP
    -0.14
    ickey
    -0.14
    olume
    -0.14
    POSITIVE LOGITS
     Pit
    0.14
     wi
    0.14
    иÑĨ
    0.13
     Prompt
    0.13
     polar
    0.13
    ail
    0.13
    _definitions
    0.13
     Proud
    0.13
    .parsers
    0.13
    anto
    0.13
    Act Density 0.008%

    No Known Activations