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

    Neuronpedia

    INDEX
    Explanations

    email addresses

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     uncertainties
    -0.66
     unwelcome
    -0.65
     undue
    -0.65
     superflu
    -0.64
     unnecessary
    -0.64
     margins
    -0.63
     waiter
    -0.63
     pressures
    -0.63
     garn
    -0.63
     hypoc
    -0.62
    POSITIVE LOGITS
    wm
    1.04
    tm
    0.98
    xp
    0.98
    dn
    0.98
    bg
    0.96
    sum
    0.96
    r
    0.96
    hyde
    0.96
    nc
    0.95
    docker
    0.93
    Act Density 0.093%

    No Known Activations