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

    Neuronpedia

    INDEX
    Explanations

    instances of assertions and descriptions within code blocks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.93
     (‘
    -0.82
     („
    -0.73
    ementara
    -0.71
    хьтан
    -0.70
     («
    -0.68
     betweenstory
    -0.68
     laſſen
    -0.68
     (“
    -0.66
     wireType
    -0.65
    POSITIVE LOGITS
    }{*}{
    0.43
     člověk
    0.40
     "
    0.38
    "
    0.38
    ướt
    0.37
    '
    0.37
     Erscheinung
    0.36
     příslu
    0.35
     çalışan
    0.35
    warnai
    0.33
    Act Density 0.277%

    No Known Activations