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

    Neuronpedia

    INDEX
    Explanations

    sequences of numeric characters or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Roskov
    -0.85
     <<<<<<<<<<<<<<
    -0.82
     Houſe
    -0.76
    MemoryWarning
    -0.71
     المعيارى
    -0.71
     ब्रेकडाउन
    -0.71
    ſelf
    -0.70
     Anſ
    -0.69
     виправивши
    -0.69
    ंदीखरीदारी
    -0.68
    POSITIVE LOGITS
     sustancia
    0.48
     ligera
    0.46
     novedad
    0.45
     escalera
    0.44
     especialidad
    0.43
     linguagem
    0.43
     subida
    0.42
     vaisseaux
    0.41
     leyenda
    0.41
     supplémentaire
    0.41
    Act Density 0.672%

    No Known Activations