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

    Neuronpedia

    INDEX
    Explanations

    references to celebrities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of celebrities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nerg
    -0.70
    THER
    -0.64
    gger
    -0.61
     Agg
    -0.60
    abus
    -0.59
    ña
    -0.59
     Wonderland
    -0.59
     condition
    -0.58
    plet
    -0.58
    yg
    -0.58
    POSITIVE LOGITS
    rities
    1.38
     celebrities
    1.03
    hips
    0.84
    ervative
    0.82
     endors
    0.80
    ervatives
    0.80
     cele
    0.78
     Celeb
    0.76
    ãħĭ
    0.75
     Cosponsors
    0.73
    Act Density 0.013%

    No Known Activations