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

    Neuronpedia

    INDEX
    Explanations

    contractions and forms of the verb "to be" in varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azi
    -0.15
    enberg
    -0.15
    μÏĨ
    -0.14
    inf
    -0.14
    kes
    -0.14
    orf
    -0.14
    enburg
    -0.14
    uetype
    -0.13
    uai
    -0.13
    hai
    -0.13
    POSITIVE LOGITS
    chy
    0.17
    comed
    0.15
    afa
    0.15
    uition
    0.15
    felt
    0.14
    pile
    0.14
    MimeType
    0.14
    adic
    0.14
    ênh
    0.13
    ascus
    0.13
    Act Density 0.229%

    No Known Activations