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

    Neuronpedia

    INDEX
    Explanations

    instances of user interface elements or commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.01
    2:0.15
    3:0.10
    4:0.06
    5:0.04
    6:0.13
    7:0.11
    8:0.09
    9:0.06
    10:0.08
    11:0.06
    Negative Logits
    urers
    -1.54
    properties
    -1.51
    ablished
    -1.50
    ーティ
    -1.41
     Historically
    -1.38
    taining
    -1.33
    ruary
    -1.33
    kefeller
    -1.32
    worldly
    -1.31
    erv
    -1.31
    POSITIVE LOGITS
     Cancel
    1.82
     endif
    1.79
     guiActive
    1.72
    endif
    1.70
    Repeat
    1.60
     pause
    1.56
    malink
    1.56
    Animation
    1.53
     shudder
    1.49
    ])
    1.48
    Act Density 0.000%

    No Known Activations