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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.08
    2:0.07
    3:0.08
    4:0.09
    5:0.06
    6:0.08
    7:0.07
    8:0.09
    9:0.06
    10:0.08
    11:0.08
    Negative Logits
    =-=-=-=-
    -3.06
    \/\/
    -3.06
    angles
    -2.72
    anship
    -2.69
    Stretch
    -2.54
    mens
    -2.53
    gom
    -2.52
     wills
    -2.52
     arrang
    -2.46
    taboola
    -2.46
    POSITIVE LOGITS
     Catalyst
    3.43
     NT
    3.15
     MSM
    2.94
     Rhino
    2.72
     RN
    2.70
     Channel
    2.67
     GHC
    2.63
     NH
    2.62
     CBC
    2.62
     AUD
    2.57
    Act Density 0.000%

    No Known Activations