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

    Neuronpedia

    INDEX
    Explanations

    exclamations or phrases expressing strong emotions

    oai_token-act-pair · gpt-3.5-turbo

    special characters and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Roc
    -0.78
     Saga
    -0.72
     sidx
    -0.65
     scattering
    -0.65
     Worlds
    -0.64
     Peb
    -0.63
     Princ
    -0.63
     Somerset
    -0.62
     Glou
    -0.61
     Voyager
    -0.61
    POSITIVE LOGITS
    º
    0.98
    âĹ¼
    0.96
    ¹
    0.89
    ¬
    0.88
    ¯
    0.83
    ISIS
    0.81
    âĢķ
    0.79
    enza
    0.78
    âĢł
    0.78
    ı
    0.77
    Act Density 0.325%

    No Known Activations