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

    Neuronpedia

    INDEX
    Explanations

    mentions of celebrities

    oai_token-act-pair · gpt-3.5-turbo

    references to celebrities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OTS
    -0.78
    unda
    -0.76
    ¸
    -0.76
    ¾
    -0.75
    anus
    -0.74
    ¼
    -0.73
    arten
    -0.72
    etheless
    -0.72
    choes
    -0.71
    YA
    -0.71
    POSITIVE LOGITS
     endors
    1.23
    rities
    1.10
     gossip
    1.09
     endorsements
    1.06
     chef
    1.00
     nude
    0.92
     chefs
    0.90
     TMZ
    0.88
     Celeb
    0.85
     entertain
    0.84
    Act Density 0.086%

    No Known Activations