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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases, particularly definite articles and demonstratives in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.41
    1:0.02
    2:0.01
    3:0.10
    4:0.03
    5:0.10
    6:0.03
    7:0.03
    8:0.14
    9:0.04
    10:0.01
    11:0.03
    Negative Logits
     understatement
    -1.66
    erity
    -1.64
     Mane
    -1.50
     Argument
    -1.49
     Delay
    -1.46
    ionage
    -1.45
    atto
    -1.44
     Demand
    -1.44
     Honour
    -1.43
     Architects
    -1.41
    POSITIVE LOGITS
     corners
    2.24
     corridors
    2.05
    yards
    1.84
     halls
    1.82
     necks
    1.80
     yards
    1.79
     valleys
    1.75
     corner
    1.71
     blocks
    1.67
    forums
    1.67
    Act Density 0.009%

    No Known Activations