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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names of people

    oai_token-act-pair · gpt-3.5-turbo

    names of notable individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    taboola
    -0.85
     td
    -0.81
    dayName
    -0.78
    iminary
    -0.78
    tml
    -0.77
    bidden
    -0.74
    cffffcc
    -0.71
     IMAGES
    -0.69
    inct
    -0.69
    unct
    -0.69
    POSITIVE LOGITS
     Kardashian
    0.96
     Hansen
    0.90
     Ryder
    0.89
     Cage
    0.87
     Hardy
    0.87
     Jenner
    0.86
     Bieber
    0.86
     Roberts
    0.86
     Reed
    0.84
     Robbins
    0.83
    Act Density 0.356%

    No Known Activations