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

    Neuronpedia

    INDEX
    Explanations

    The main thing this neuron does is find names related to specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names, particularly "Wade" and "Chen."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾įå
    -0.81
    gio
    -0.73
    ļ
    -0.73
    Ľ
    -0.72
    adelphia
    -0.71
    phant
    -0.71
    ariat
    -0.70
    asury
    -0.70
    ī
    -0.70
    orie
    -0.70
    POSITIVE LOGITS
    nesday
    0.87
     Wink
    0.78
     Bauer
    0.78
     Wade
    0.74
    erers
    0.67
     Spin
    0.66
    arella
    0.66
    abase
    0.66
    Pixel
    0.62
     Warm
    0.61
    Act Density 0.058%

    No Known Activations