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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "seen" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leonard
    -0.15
    amente
    -0.15
     preferredStyle
    -0.14
    sson
    -0.14
    ayed
    -0.14
    urer
    -0.14
    peat
    -0.14
    ennes
    -0.13
    viders
    -0.13
    fen
    -0.13
    POSITIVE LOGITS
     Kay
    0.17
    eyer
    0.17
    Kay
    0.16
    ι
    0.16
    _rpc
    0.15
    ouser
    0.14
     kolo
    0.14
    Hel
    0.14
    çİ
    0.14
    icast
    0.14
    Act Density 0.037%

    No Known Activations