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

    Neuronpedia

    INDEX
    Explanations

    references to different dialects and their linguistic influences

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dialects and consciousness concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ctions
    -0.76
    med
    -0.72
    FORE
    -0.70
    WAYS
    -0.68
    coni
    -0.67
    bor
    -0.67
    pha
    -0.66
    scill
    -0.66
    anu
    -0.64
    cin
    -0.63
    POSITIVE LOGITS
    es
    0.88
    ij士
    0.87
    ysis
    0.84
    hner
    0.81
    ĪĴ
    0.81
    yip
    0.78
    ensional
    0.77
    hip
    0.76
    ongyang
    0.76
    ngth
    0.73
    Act Density 0.045%

    No Known Activations