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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly quotes and periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TemporalType
    -0.72
    thood
    -0.65
    TestingModule
    -0.63
    icles
    -0.62
     timeType
    -0.61
    IndentedString
    -0.61
    хьтан
    -0.60
     MessageBoxIcon
    -0.60
    evos
    -0.60
    ….”
    -0.59
    POSITIVE LOGITS
    ’
    0.42
     Universitaria
    0.37
     "
    0.34
     turística
    0.34
    "
    0.34
     flotante
    0.33
     trasero
    0.32
     turístico
    0.32
     touristique
    0.32
     iluminación
    0.32
    Act Density 0.398%

    No Known Activations