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

    Neuronpedia

    INDEX
    Explanations

    numbers and statistics in the form of amounts, quantities, or measurements

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     boun
    -0.68
    ©¶æ
    -0.65
     Bang
    -0.64
     heartbeat
    -0.64
    é¾įå¥ij士
    -0.63
     Ammunition
    -0.63
     Univers
    -0.62
     experien
    -0.62
     bleeding
    -0.61
     Grab
    -0.61
    POSITIVE LOGITS
    cv
    0.83
    604
    0.81
    ax
    0.80
    rg
    0.79
    minus
    0.77
    dc
    0.76
    ths
    0.76
    bm
    0.76
    orah
    0.74
    tesy
    0.74
    Act Density 0.067%

    No Known Activations