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

    Neuronpedia

    INDEX
    Explanations

    numerical expressions and variables representing quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     iſt
    -0.73
     vestig
    -0.72
     ―――――
    -0.70
     lepro
    -0.68
     elog
    -0.68
     Schä
    -0.67
     Recom
    -0.66
     karo
    -0.66
    ſel
    -0.66
    terday
    -0.66
    POSITIVE LOGITS
     n
    1.37
    n
    1.29
    nnn
    1.06
     N
    1.04
    setN
    1.00
     Cn
    0.98
    𝗻
    0.95
    nT
    0.94
    N
    0.93
    nn
    0.92
    Act Density 0.188%

    No Known Activations