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

    Neuronpedia

    INDEX
    Explanations

    statistics or numerical information related to specific demographics

    oai_token-act-pair · gpt-3.5-turbo

    frequent numerical ratios or statistics related to populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ffen
    -0.65
    BO
    -0.62
    issance
    -0.59
    Joined
    -0.57
     misunder
    -0.56
     status
    -0.55
     void
    -0.55
    BALL
    -0.54
    ymm
    -0.54
     balances
    -0.53
    POSITIVE LOGITS
     ten
    0.98
     five
    0.92
     10
    0.90
    irteen
    0.89
    dozen
    0.88
    elfth
    0.86
    ousand
    0.85
    undred
    0.85
    illion
    0.83
    escap
    0.82
    Act Density 0.040%

    No Known Activations