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

    Neuronpedia

    INDEX
    Explanations

    programming-related constructs, particularly function calls and conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cel
    -0.47
     Bul
    -0.45
    EREN
    -0.44
     Ul
    -0.43
     Ig
    -0.42
     Rap
    -0.41
     Af
    -0.40
    DERE
    -0.40
     Hip
    -0.40
     Promo
    -0.40
    POSITIVE LOGITS
     err
    1.86
    err
    1.72
     arr
    1.23
    arr
    1.21
    Err
    1.12
     Err
    1.09
     Terr
    0.92
    urr
    0.91
     Arr
    0.91
    Arr
    0.82
    Act Density 0.233%

    No Known Activations