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

    Neuronpedia

    INDEX
    Explanations

    phrases containing a mix of special characters and letters in a specific pattern

    oai_token-act-pair · gpt-3.5-turbo

    special characters or sequences of non-standard textual elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bonded
    -0.83
    cius
    -0.82
    zanne
    -0.76
     bour
    -0.76
     dominated
    -0.76
    iche
    -0.76
     hoax
    -0.75
     indicted
    -0.75
     rigged
    -0.69
     presidency
    -0.68
    POSITIVE LOGITS
    ãĤĭ
    1.91
    ãģĦ
    1.88
    ãģ
    1.88
    ãģ¾
    1.78
    ãĤ
    1.78
    ãĤī
    1.77
    ãģª
    1.76
    ãģĹ
    1.75
    ãģŁ
    1.72
    ãģĵ
    1.68
    Act Density 0.014%

    No Known Activations