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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĬ¬
    -0.19
    unj
    -0.16
    >manual
    -0.15
    >NN
    -0.15
    strup
    -0.14
    bourg
    -0.14
     glEnable
    -0.14
    uzey
    -0.14
    andler
    -0.14
     giai
    -0.14
    POSITIVE LOGITS
     below
    0.23
     minus
    0.23
     bottom
    0.23
     Bottom
    0.22
     down
    0.21
     negative
    0.21
     convers
    0.21
    NegativeButton
    0.20
    bottom
    0.20
     lower
    0.20
    Act Density 0.263%

    No Known Activations