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

    Neuronpedia

    INDEX
    Explanations

    numerical values and comparisons in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.05
    2:0.17
    3:0.09
    4:0.01
    5:0.02
    6:0.09
    7:0.11
    8:0.08
    9:0.07
    10:0.08
    11:0.16
    Negative Logits
    iris
    -1.07
    udo
    -0.96
    quer
    -0.90
    ��
    -0.90
    reon
    -0.89
     Fiat
    -0.86
     Tig
    -0.84
    uta
    -0.83
     kindly
    -0.83
     Wanted
    -0.82
    POSITIVE LOGITS
    ANE
    0.99
     accol
    0.95
    isSpecialOrderable
    0.94
    EFF
    0.90
    APD
    0.89
    tons
    0.88
    ijk
    0.88
     footprint
    0.88
    ERAL
    0.87
    ORPG
    0.86
    Act Density 0.099%

    No Known Activations