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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical cords, wires, or connections

    oai_token-act-pair · gpt-3.5-turbo

    references to "cord" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     IMAGES
    -0.75
    ggies
    -0.66
    iesta
    -0.65
    visible
    -0.62
     Atmosp
    -0.61
     Naz
    -0.59
    hh
    -0.58
    hammad
    -0.58
    ĨĴ
    -0.57
    veyard
    -0.56
    POSITIVE LOGITS
     cord
    1.39
     cords
    0.95
    lessly
    0.90
     Cord
    0.88
    iac
    0.87
    ovan
    0.86
    ret
    0.84
    oba
    0.79
    weed
    0.78
    ages
    0.78
    Act Density 0.006%

    No Known Activations