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

    Neuronpedia

    INDEX
    Explanations

    add-ons and optional features for projects or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.16
    3:0.04
    4:0.06
    5:0.03
    6:0.16
    7:0.09
    8:0.03
    9:0.04
    10:0.22
    11:0.08
    Negative Logits
    ��
    -1.70
    �
    -1.57
     Topics
    -1.46
    nton
    -1.38
     Sloan
    -1.36
     Rosenthal
    -1.36
     Compton
    -1.36
     Siem
    -1.35
     Scholar
    -1.30
     lect
    -1.28
    POSITIVE LOGITS
     procurement
    1.82
    addons
    1.79
     installer
    1.69
    merce
    1.69
    assault
    1.63
    quer
    1.59
     repositories
    1.49
     bidder
    1.47
    Factory
    1.44
     shell
    1.43
    Act Density 0.001%

    No Known Activations