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

    occurrences and references to celebrities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    choes
    -0.92
    hematic
    -0.85
    anus
    -0.82
    THER
    -0.76
    ¼
    -0.75
    doors
    -0.74
    tered
    -0.74
    ¾
    -0.72
    atives
    -0.71
    ¸
    -0.70
    POSITIVE LOGITS
    rities
    1.06
     endorsements
    1.03
     endors
    0.97
     chef
    0.95
    wcs
    0.89
     gossip
    0.89
     chefs
    0.88
     celebrities
    0.83
     idols
    0.82
     celebrity
    0.79
    Act Density 0.028%

    No Known Activations