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

    Neuronpedia

    INDEX
    Explanations

    occurrences of frequently used words and grammatical structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sadd
    -0.15
    еÑĪ
    -0.15
    owell
    -0.15
    stown
    -0.15
    ή
    -0.15
     Kür
    -0.15
    prises
    -0.14
    /callback
    -0.14
    ЧеÑĢ
    -0.14
     dro
    -0.13
    POSITIVE LOGITS
    uce
    0.15
     Majority
    0.15
    mere
    0.15
    ικο
    0.15
    åĪ°åºķ
    0.15
    .Unity
    0.14
     Ment
    0.14
    igu
    0.14
    uj
    0.14
    848
    0.14
    Act Density 0.001%

    No Known Activations