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

    Neuronpedia

    INDEX
    Explanations

    complex composed characters or character combinations

    oai_token-act-pair · gpt-3.5-turbo

    sequences of obscure characters or symbols that may indicate specialized content or encoding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xus
    -0.97
    lycer
    -0.95
    oche
    -0.87
    olit
    -0.82
    ffen
    -0.82
    orne
    -0.80
    ulously
    -0.79
    atche
    -0.78
    tera
    -0.77
    eways
    -0.77
    POSITIVE LOGITS
    ãģ¦
    1.75
    ãģĦ
    1.68
    ãĤĭ
    1.60
    ãģ
    1.56
    ãģŁ
    1.53
    ãģ¾
    1.51
    ãĤĵ
    1.49
    ãģª
    1.47
    ãĤī
    1.46
    ãĤ
    1.42
    Act Density 0.011%

    No Known Activations