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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tæ
    -0.56
    woł
    -0.52
     hire
    -0.52
    UGH
    -0.50
     von
    -0.49
    ITOR
    -0.47
    իտ
    -0.47
    OKING
    -0.46
    itere
    -0.46
     Kata
    -0.46
    POSITIVE LOGITS
    ########.
    0.85
     Anſ
    0.82
     pleaſure
    0.81
     ſtand
    0.80
     ſche
    0.79
     myſelf
    0.78
     purpoſe
    0.78
     miſ
    0.77
     الرياضيه
    0.77
     насељу
    0.76
    Act Density 0.311%

    No Known Activations