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

    Neuronpedia

    INDEX
    Explanations

    mentions of celebrities and notable figures, often in the context of fame and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pauvres
    -0.67
     traditionnels
    -0.60
    mtrl
    -0.57
     Micho
    -0.57
     mères
    -0.56
    XtraGrid
    -0.54
     travailleurs
    -0.53
    collate
    -0.53
     Arlene
    -0.53
     surla
    -0.52
    POSITIVE LOGITS
     Medal
    0.88
     medal
    0.87
     celebrity
    0.85
    клопе
    0.85
     Jimmy
    0.79
     Celebrity
    0.79
     Cold
    0.77
    Jimmy
    0.75
     autorytatywna
    0.75
     rally
    0.73
    Act Density 0.098%

    No Known Activations