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

    Neuronpedia

    INDEX
    Explanations

    numerical references and identifiers in academic citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tremend
    -0.60
    rongh
    -0.59
    ongh
    -0.57
     prem
    -0.56
    rium
    -0.55
    efully
    -0.54
    ilts
    -0.54
    rika
    -0.53
    reek
    -0.53
    hetical
    -0.53
    POSITIVE LOGITS
    Merit
    0.68
     Magicka
    0.61
    ãģ®æ
    0.59
     Papers
    0.58
     Starcraft
    0.58
    GMT
    0.56
     Journals
    0.56
    çİĭ
    0.56
    éĽ
    0.55
    ayer
    0.55
    Act Density 0.034%

    No Known Activations