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

    Neuronpedia

    INDEX
    Explanations

    references to high-stakes situations or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DSA
    -0.17
    ÑĤÑĮ
    -0.16
    adaki
    -0.15
    uai
    -0.15
    oler
    -0.14
    CharCode
    -0.14
    azine
    -0.14
     Bain
    -0.14
     rather
    -0.13
    achsen
    -0.13
    POSITIVE LOGITS
    343
    0.17
    gle
    0.15
    ien
    0.14
    iá»ĩn
    0.14
    REDIENT
    0.14
     Hear
    0.14
    \Context
    0.13
    ener
    0.13
    bern
    0.13
    à¸ģว
    0.13
    Act Density 0.008%

    No Known Activations