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

    Neuronpedia

    INDEX
    Explanations

    C++ type definitions and related declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.16
    1:0.20
    2:0.06
    3:0.06
    4:0.06
    5:0.12
    6:0.06
    7:0.05
    8:0.05
    9:0.05
    10:0.04
    11:0.04
    Negative Logits
    pedia
    -1.74
     certific
    -1.68
    zn
    -1.57
     Bog
    -1.57
    ornia
    -1.51
     fraud
    -1.50
     countryside
    -1.50
     horizont
    -1.49
    opian
    -1.48
     doomed
    -1.47
    POSITIVE LOGITS
    ��
    1.94
    �
    1.86
    �
    1.79
    �
    1.76
    ::
    1.73
    �
    1.64
    �
    1.62
    (&
    1.61
    atch
    1.58
    ��
    1.57
    Act Density 0.000%

    No Known Activations