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

    Neuronpedia

    INDEX
    Explanations

    words related to facial hair

    oai_token-act-pair · gpt-3.5-turbo

    references to the character Bluebeard

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     alloy
    -0.72
     Idol
    -0.62
     wheels
    -0.62
     Jinping
    -0.62
     hood
    -0.61
     comprom
    -0.61
     tong
    -0.61
     vest
    -0.59
     cooperative
    -0.59
     util
    -0.59
    POSITIVE LOGITS
    beard
    1.92
    initions
    0.77
    ulf
    0.71
    andr
    0.69
    APD
    0.68
    zsche
    0.67
    runs
    0.66
    pard
    0.66
    forth
    0.66
    estyle
    0.65
    Act Density 0.002%

    No Known Activations