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

    Neuronpedia

    INDEX
    Explanations

    references to statues and monuments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.10
    2:0.01
    3:0.12
    4:0.03
    5:0.08
    6:0.05
    7:0.02
    8:0.41
    9:0.05
    10:0.01
    11:0.01
    Negative Logits
    ussen
    -1.83
     Blend
    -1.76
     Advantage
    -1.75
     coefficient
    -1.74
     interactions
    -1.73
    lon
    -1.73
     nerv
    -1.72
     Guer
    -1.67
     relationships
    -1.65
     exchanges
    -1.65
    POSITIVE LOGITS
     erected
    2.86
     statue
    2.64
     statues
    2.43
     pedest
    2.41
     monument
    2.39
     vener
    2.34
     monuments
    2.33
     honoring
    2.30
     commemor
    2.25
     memorial
    2.25
    Act Density 0.030%

    No Known Activations