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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating equivalence or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hong
    -0.17
    ught
    -0.15
    à¸ī
    -0.15
    duk
    -0.14
    /animate
    -0.14
    essler
    -0.14
    EG
    -0.14
    EMA
    -0.14
    ŀ
    -0.14
    splash
    -0.14
    POSITIVE LOGITS
    ivalent
    0.20
    (=)
    0.17
    AndHashCode
    0.17
    ivant
    0.17
    entially
    0.16
    ential
    0.16
     æĸ¼
    0.16
    wert
    0.15
    alse
    0.15
    ritis
    0.15
    Act Density 0.013%

    No Known Activations