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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks indicating end of thoughts or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elf
    -0.15
     Zimmer
    -0.14
    Ã¤ÃŁ
    -0.14
    irim
    -0.14
    eller
    -0.14
    DataSet
    -0.13
    ÑĢой
    -0.13
     vyž
    -0.13
    enschaft
    -0.13
     Exec
    -0.13
    POSITIVE LOGITS
    PTY
    0.15
    opis
    0.14
    avin
    0.14
    ovit
    0.14
    onas
    0.14
    BOOST
    0.14
    mina
    0.13
    ccount
    0.13
    sov
    0.13
    dle
    0.13
    Act Density 0.005%

    No Known Activations