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

    Neuronpedia

    INDEX
    Explanations

    phrases related to copyright and permissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hek
    -0.16
    978
    -0.15
    976
    -0.15
    anki
    -0.15
     Palo
    -0.15
    raki
    -0.14
    omy
    -0.14
    patches
    -0.14
    رج
    -0.14
    hasMany
    -0.14
    POSITIVE LOGITS
    appen
    0.16
     æĵ
    0.15
    DCF
    0.15
    oth
    0.14
     any
    0.14
     nor
    0.14
     WHATSOEVER
    0.14
    ESIS
    0.14
    ette
    0.14
     unless
    0.14
    Act Density 0.011%

    No Known Activations