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

    Neuronpedia

    INDEX
    Explanations

    expressions related to the concept of endings and beginnings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.02
    2:0.11
    3:0.08
    4:0.10
    5:0.03
    6:0.16
    7:0.12
    8:0.04
    9:0.04
    10:0.09
    11:0.10
    Negative Logits
    heit
    -1.56
     evils
    -1.54
    hemy
    -1.49
    rimination
    -1.43
    Compat
    -1.42
    ommod
    -1.38
    ildo
    -1.37
     destiny
    -1.32
     dependence
    -1.31
     heterogeneity
    -1.31
    POSITIVE LOGITS
    noon
    1.57
     Lancaster
    1.48
     Nicholson
    1.47
    GMT
    1.45
     Autumn
    1.42
    heads
    1.41
     Harding
    1.40
    mitter
    1.39
     Booth
    1.36
     Bie
    1.36
    Act Density 0.019%

    No Known Activations