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

    Neuronpedia

    INDEX
    Explanations

    references to time durations or historical experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.71
    twimg
    -0.56
    IntoConstraints
    -0.47
    awtextra
    -0.45
     Normdatei
    -0.43
    makeConstraints
    -0.43
    يكب
    -0.43
    HXLINE
    -0.41
     betweenstory
    -0.39
     facie
    -0.38
    POSITIVE LOGITS
     jamais
    0.40
     فريبيس
    0.39
    hapsody
    0.38
    Entire
    0.37
     never
    0.37
     Entire
    0.36
    batim
    0.36
    Dati
    0.36
    theim
    0.35
    telli
    0.35
    Act Density 0.529%

    No Known Activations