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

    Neuronpedia

    INDEX
    Explanations

    programming commands or syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oty
    -0.16
    lagen
    -0.16
    leston
    -0.15
     ModelState
    -0.15
    rette
    -0.15
    phem
    -0.15
     Majesty
    -0.15
    bak
    -0.14
    emd
    -0.14
    ovy
    -0.14
    POSITIVE LOGITS
    asc
    0.16
    wart
    0.16
    BO
    0.16
    vet
    0.16
    DL
    0.15
    anh
    0.15
    ard
    0.15
    ythe
    0.15
     Holy
    0.14
    ud
    0.14
    Act Density 0.020%

    No Known Activations