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

    Neuronpedia

    INDEX
    Explanations

    the word "of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.08
    2:0.08
    3:0.09
    4:0.08
    5:0.08
    6:0.08
    7:0.09
    8:0.08
    9:0.08
    10:0.07
    11:0.06
    Negative Logits
     helic
    -2.77
    -+-+
    -2.69
    brid
    -2.66
    vati
    -2.61
    geoning
    -2.57
     downed
    -2.45
    amily
    -2.41
    unia
    -2.40
    >(
    -2.38
    >]
    -2.38
    POSITIVE LOGITS
     Nero
    2.88
     Nasa
    2.82
    inho
    2.79
     EUR
    2.76
     Adidas
    2.75
     Polo
    2.67
     Zeit
    2.67
     Europa
    2.58
     KD
    2.55
     Agric
    2.51
    Act Density 0.000%

    No Known Activations