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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of individuals or entities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     betweenstory
    -1.06
    Personendaten
    -1.00
    aarrggbb
    -0.92
    DoubleQuotes
    -0.92
     CURIAM
    -0.90
     itſelf
    -0.90
     تضيفلها
    -0.87
    writeField
    -0.86
     виправивши
    -0.85
     kaarangay
    -0.84
    POSITIVE LOGITS
     o
    0.45
    m
    0.44
    w
    0.42
    se
    0.40
    black
    0.39
     şi
    0.39
     Gew
    0.39
    p
    0.39
    o
    0.38
    la
    0.38
    Act Density 0.007%

    No Known Activations