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

    Neuronpedia

    INDEX
    Explanations

    references to distances and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.11
    3:0.04
    4:0.07
    5:0.01
    6:0.06
    7:0.36
    8:0.02
    9:0.03
    10:0.12
    11:0.10
    Negative Logits
     postpone
    -1.60
     postponed
    -1.45
    reciation
    -1.44
     outp
    -1.43
     Anniversary
    -1.40
     Month
    -1.40
     morale
    -1.39
     celebrations
    -1.39
     Feast
    -1.37
    elight
    -1.36
    POSITIVE LOGITS
    know
    1.63
    heast
    1.58
    prints
    1.47
    agle
    1.43
     treacherous
    1.40
    outheast
    1.39
     Guides
    1.38
    west
    1.33
    uzzle
    1.32
     bends
    1.30
    Act Density 0.029%

    No Known Activations