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

    Neuronpedia

    INDEX
    Explanations

    phrases related to coding and programming

    oai_token-act-pair · gpt-3.5-turbo

    elements related to programming or coding concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Others
    -0.79
     downright
    -0.65
    itage
    -0.64
     surprises
    -0.64
     unofficial
    -0.63
    lations
    -0.62
    agy
    -0.62
     giveaways
    -0.62
    tro
    -0.62
     loopholes
    -0.62
    POSITIVE LOGITS
     Suppose
    1.54
     suppose
    1.02
     hypot
    0.96
     \(
    0.90
    foo
    0.90
     foo
    0.88
     XY
    0.85
    Supp
    0.85
    say
    0.84
     imagine
    0.84
    Act Density 0.420%

    No Known Activations