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

    Neuronpedia

    INDEX
    Explanations

    forms of the verb "to be" and related action or state descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ฺ
    -0.15
    resden
    -0.15
    tings
    -0.15
    ÎŃνÏĦ
    -0.14
    à§į
    -0.14
    ázd
    -0.14
     NAMES
    -0.14
    Ìģt
    -0.14
    Ìģ
    -0.14
    FER
    -0.13
    POSITIVE LOGITS
     Mol
    0.15
    oller
    0.15
     count
    0.14
    δά
    0.14
     thr
    0.14
    onse
    0.14
    ioni
    0.14
    acin
    0.14
    ochen
    0.14
    athi
    0.14
    Act Density 0.012%

    No Known Activations