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

    Neuronpedia

    INDEX
    Explanations

    numerals and symbols such as special characters

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or topic signified by the special character sequence 'ÂŃ'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wagen
    -0.83
    aimon
    -0.81
    otine
    -0.74
    owell
    -0.73
    unks
    -0.72
    idad
    -0.71
    cius
    -0.69
    hattan
    -0.67
    izu
    -0.67
     NX
    -0.66
    POSITIVE LOGITS
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.89
     ÂŃ
    0.88
    ··
    0.84
    âĢij
    0.83
    ——
    0.83
    £
    0.81
    âĨ
    0.80
    POL
    0.78
    Ëľ
    0.78
    Nev
    0.78
    Act Density 0.004%

    No Known Activations