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

    Neuronpedia

    INDEX
    Explanations

    references to community services and support systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.04
    2:0.05
    3:0.07
    4:0.04
    5:0.04
    6:0.29
    7:0.02
    8:0.03
    9:0.22
    10:0.02
    11:0.03
    Negative Logits
     Sparrow
    -3.45
     Ralph
    -3.39
     Sweeney
    -3.38
     Firefly
    -3.35
     Floyd
    -3.34
     Luffy
    -3.22
     Yaz
    -3.18
    ript
    -3.13
    Billy
    -3.10
    Jere
    -3.09
    POSITIVE LOGITS
     centers
    7.50
     center
    7.02
     centres
    7.02
    Center
    6.99
     centre
    6.66
     Center
    6.65
    center
    6.34
     Centre
    6.08
     CENT
    5.64
    Cent
    5.53
    Act Density 0.026%

    No Known Activations