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

    Neuronpedia

    INDEX
    Explanations

    phrases related to processes or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.14
    2:0.02
    3:0.05
    4:0.03
    5:0.03
    6:0.06
    7:0.02
    8:0.02
    9:0.51
    10:0.02
    11:0.02
    Negative Logits
     Flores
    -3.55
     mole
    -3.52
     Kemp
    -3.44
    ayan
    -3.28
    aches
    -3.28
    aya
    -3.19
    anka
    -3.17
    oles
    -2.99
    aun
    -2.97
    hw
    -2.96
    POSITIVE LOGITS
    3
    4.88
     3
    4.87
    03
    3.94
     03
    3.85
     III
    3.75
    2003
    3.74
     303
    3.71
     cous
    3.65
    393
    3.52
     2003
    3.52
    Act Density 0.165%

    No Known Activations