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

    Neuronpedia

    INDEX
    Explanations

    references to specific services or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.03
    2:0.07
    3:0.05
    4:0.05
    5:0.05
    6:0.21
    7:0.04
    8:0.06
    9:0.26
    10:0.03
    11:0.03
    Negative Logits
    Rh
    -4.04
     Shoals
    -3.90
     rall
    -3.60
     polio
    -3.53
    rh
    -3.44
    Ros
    -3.43
     prol
    -3.38
    Fla
    -3.32
     Richardson
    -3.25
     Ros
    -3.20
    POSITIVE LOGITS
     Century
    8.05
     Cent
    7.11
    Cent
    6.75
     Millennium
    5.04
     cent
    4.81
     CENT
    4.68
     Centauri
    4.51
    cent
    4.44
     Cad
    4.43
    icent
    4.24
    Act Density 0.002%

    No Known Activations