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

    Neuronpedia

    INDEX
    Explanations

    punctuation and sentence structure indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amp
    -0.16
    angan
    -0.15
     Cumhur
    -0.14
    Others
    -0.14
     Others
    -0.14
    ampie
    -0.14
    áli
    -0.14
    è¿ĩåİ»
    -0.14
     Ulus
    -0.14
    others
    -0.14
    POSITIVE LOGITS
    stadt
    0.19
    ium
    0.16
    rix
    0.14
     compared
    0.14
    689
    0.14
    âĸį
    0.14
     actually
    0.14
     Worm
    0.13
    bes
    0.13
    mac
    0.13
    Act Density 0.008%

    No Known Activations