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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating an increase in readership or engagement over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.16
    3:0.19
    4:0.12
    5:0.02
    6:0.07
    7:0.14
    8:0.07
    9:0.04
    10:0.05
    11:0.05
    Negative Logits
     hindsight
    -1.80
    onne
    -1.61
    edience
    -1.55
     intrins
    -1.51
     manag
    -1.48
     Ceres
    -1.47
    manship
    -1.44
     knots
    -1.44
    anus
    -1.42
     Wem
    -1.41
    POSITIVE LOGITS
    "]
    1.40
    aunders
    1.35
     sidx
    1.35
     Sponsor
    1.34
    ahs
    1.32
    Tour
    1.32
    iao
    1.31
     allergic
    1.31
    eligible
    1.29
    drug
    1.28
    Act Density 0.000%

    No Known Activations