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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, especially periods

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     gere
    -0.49
     salita
    -0.45
    confirmButton
    -0.43
    ("
    -0.41
     decoraciones
    -0.41
    ุก
    -0.41
     lạnh
    -0.41
     Gere
    -0.40
    PRES
    -0.40
    вата
    -0.40
    POSITIVE LOGITS
     autorytatywna
    0.90
    parsedMessage
    0.90
    DockStyle
    0.90
    يميديا
    0.80
    rairie
    0.76
    ſelf
    0.75
     bezeichneter
    0.74
    Personendaten
    0.72
     تضيفلها
    0.71
    colgroup
    0.69
    Act Density 0.015%

    No Known Activations