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

    Neuronpedia

    INDEX
    Explanations

    special characters in non-English languages

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    espie
    -0.87
     Dill
    -0.73
     Murdoch
    -0.72
     Jenkins
    -0.70
     Quadro
    -0.69
     PD
    -0.68
    wagen
    -0.67
     Dunn
    -0.66
     Carib
    -0.66
    enegger
    -0.66
    POSITIVE LOGITS
    ï¸ı
    1.00
    ĺ
    0.93
    ¹
    0.92
    £
    0.90
    Æ
    0.90
    ©
    0.89
    Ľ
    0.89
    Ĩ
    0.89
    ¸
    0.88
    ķ
    0.88
    Act Density 0.042%

    No Known Activations