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

    Neuronpedia

    INDEX
    Explanations

    the word "go" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.09
    2:0.06
    3:0.08
    4:0.09
    5:0.08
    6:0.09
    7:0.07
    8:0.10
    9:0.09
    10:0.08
    11:0.06
    Negative Logits
    ��
    -2.00
     Sasha
    -1.91
    folder
    -1.89
    xf
    -1.89
    sg
    -1.86
    src
    -1.84
    Movie
    -1.84
     Ingram
    -1.79
    bold
    -1.78
    zu
    -1.75
    POSITIVE LOGITS
     Died
    2.06
     municipality
    1.88
     pun
    1.83
     penal
    1.81
     meteor
    1.77
     secondly
    1.73
    unicip
    1.73
     meets
    1.72
     ',
    1.72
     bicycl
    1.71
    Act Density 0.000%

    No Known Activations