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

    Neuronpedia

    INDEX
    Explanations

    phrases related to image processing and referencing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.07
    3:0.07
    4:0.09
    5:0.04
    6:0.04
    7:0.36
    8:0.03
    9:0.05
    10:0.09
    11:0.06
    Negative Logits
     bargain
    -1.85
    orers
    -1.80
    glers
    -1.78
    adem
    -1.77
    Reviewer
    -1.76
     acad
    -1.69
    Deal
    -1.68
    �
    -1.65
    ETF
    -1.65
    Orig
    -1.64
    POSITIVE LOGITS
     slips
    1.74
    thin
    1.66
     defeats
    1.64
     setbacks
    1.62
     scratches
    1.61
     shoulder
    1.59
     Torn
    1.59
    iann
    1.54
     letters
    1.51
     repealed
    1.50
    Act Density 0.000%

    No Known Activations