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

    Neuronpedia

    INDEX
    Explanations

    sentences indicating official announcements or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.03
    2:0.04
    3:0.04
    4:0.06
    5:0.03
    6:0.18
    7:0.04
    8:0.09
    9:0.28
    10:0.02
    11:0.03
    Negative Logits
     Roz
    -4.11
     cryptoc
    -4.04
    Pol
    -3.99
     Warsaw
    -3.71
    ł
    -3.69
    catentry
    -3.62
    ulz
    -3.60
     Poland
    -3.56
     [&
    -3.51
     Activision
    -3.45
    POSITIVE LOGITS
     Henderson
    10.56
     Hend
    7.67
    hend
    5.60
     Hendricks
    5.13
     Edgar
    4.71
     Petersen
    4.67
     Hem
    4.39
     Kend
    4.12
     Hume
    4.06
    horn
    4.01
    Act Density 0.002%

    No Known Activations