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

    Neuronpedia

    INDEX
    Explanations

    symbols or punctuation marks used in formatting text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erre
    -0.16
    ich
    -0.16
    pri
    -0.15
     èĪ
    -0.15
    .broadcast
    -0.15
    dzi
    -0.15
    udit
    -0.14
    etti
    -0.14
     Huff
    -0.14
    -desc
    -0.14
    POSITIVE LOGITS
    uft
    0.16
     Rifle
    0.15
     kennenlernen
    0.14
     sadd
    0.14
    ôm
    0.14
    neh
    0.14
    rada
    0.14
    asures
    0.14
    ï¼Ĵï¼IJ
    0.13
    _SERIAL
    0.13
    Act Density 0.003%

    No Known Activations