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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.09
    3:0.09
    4:0.08
    5:0.07
    6:0.08
    7:0.07
    8:0.08
    9:0.08
    10:0.08
    11:0.07
    Negative Logits
    anus
    -1.96
    forth
    -1.76
    ioned
    -1.73
    Reviewed
    -1.66
    cells
    -1.66
    ��
    -1.59
    standing
    -1.56
    ��
    -1.56
     deceased
    -1.55
    phal
    -1.52
    POSITIVE LOGITS
    flix
    1.87
    wcsstore
    1.84
     bikini
    1.73
    benefit
    1.70
     endif
    1.68
     medic
    1.66
    oiler
    1.64
    acebook
    1.63
     glam
    1.60
     lifestyle
    1.58
    Act Density 0.000%

    No Known Activations