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

    Neuronpedia

    INDEX
    Explanations

    mentions of a specific name, "Dykes"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Dy" and its variations, which likely relates to a name or specific term

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sburgh
    -0.73
    insula
    -0.72
    oice
    -0.71
    姫
    -0.71
    ulators
    -0.69
    CRIP
    -0.68
     Austral
    -0.67
    ":[
    -0.67
    raints
    -0.67
    icans
    -0.66
    POSITIVE LOGITS
    gradation
    0.86
    stal
    0.83
    ston
    0.79
    brid
    0.79
    pos
    0.78
    functional
    0.78
    dy
    0.76
    nec
    0.76
    kes
    0.76
    fed
    0.76
    Act Density 0.032%

    No Known Activations