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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "of"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.08
    2:0.08
    3:0.08
    4:0.07
    5:0.09
    6:0.07
    7:0.08
    8:0.09
    9:0.08
    10:0.07
    11:0.08
    Negative Logits
    yout
    -2.87
    ranch
    -2.87
    pling
    -2.63
    interstitial
    -2.60
    ciples
    -2.60
    rollers
    -2.56
    iversal
    -2.49
    gregation
    -2.48
    Frames
    -2.48
    ibl
    -2.46
    POSITIVE LOGITS
     Aires
    3.36
     Zurich
    3.14
     Erit
    3.07
     NEC
    3.02
     Miliband
    2.96
     Eliot
    2.94
    Aust
    2.81
     Switzerland
    2.72
     Anat
    2.70
     Austrian
    2.70
    Act Density 0.000%

    No Known Activations