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

    Neuronpedia

    INDEX
    Explanations

    phrases related to programming function calls by reference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.07
    2:0.08
    3:0.08
    4:0.07
    5:0.08
    6:0.07
    7:0.08
    8:0.08
    9:0.08
    10:0.10
    11:0.08
    Negative Logits
     Baird
    -3.12
     Hatt
    -3.06
     MacDonald
    -2.68
     Hob
    -2.66
     impaired
    -2.62
     Barker
    -2.51
     Gib
    -2.48
     Neph
    -2.46
     Totem
    -2.45
     Errors
    -2.41
    POSITIVE LOGITS
     colle
    3.09
    ucl
    2.88
    gal
    2.56
    CLA
    2.54
     declass
    2.47
     unlock
    2.46
    "],"
    2.46
     arsenal
    2.45
     prest
    2.45
    LAN
    2.45
    Act Density 0.000%

    No Known Activations