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

    Neuronpedia

    INDEX
    Explanations

    terms related to design and usability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.06
    2:0.06
    3:0.06
    4:0.04
    5:0.04
    6:0.24
    7:0.03
    8:0.04
    9:0.27
    10:0.03
    11:0.02
    Negative Logits
     McM
    -4.41
     Bundy
    -3.78
     McMahon
    -3.73
     Echoes
    -3.72
     Malone
    -3.68
    ��
    -3.65
     Barkley
    -3.47
     whisky
    -3.44
     Highland
    -3.42
     Parenthood
    -3.40
    POSITIVE LOGITS
    design
    6.48
     Design
    6.38
    Design
    6.30
     design
    6.05
     Designs
    5.54
     designs
    5.43
     redesign
    5.42
     designers
    5.29
     designer
    5.24
     designing
    5.19
    Act Density 0.010%

    No Known Activations