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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "des."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alez
    -0.16
     Narrative
    -0.15
    ity
    -0.15
     Bib
    -0.14
    gow
    -0.14
     tend
    -0.14
     Ston
    -0.14
     Stap
    -0.14
     impulse
    -0.14
    ï¿
    -0.14
    POSITIVE LOGITS
    yne
    0.18
     Kür
    0.17
    inoa
    0.17
    ORIES
    0.16
    abei
    0.16
    elters
    0.15
    سÙĪب
    0.15
    uelle
    0.14
    iju
    0.14
    емÑĥ
    0.14
    Act Density 0.004%

    No Known Activations