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

    Neuronpedia

    INDEX
    Explanations

    elements related to settings and updates in a software or device context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.10
    1:0.02
    2:0.18
    3:0.13
    4:0.10
    5:0.03
    6:0.05
    7:0.04
    8:0.05
    9:0.05
    10:0.09
    11:0.10
    Negative Logits
     disproportionately
    -1.70
     primed
    -1.66
     strikingly
    -1.66
     leftover
    -1.66
     stagger
    -1.65
    upon
    -1.61
     mechanically
    -1.59
     tantal
    -1.58
    agically
    -1.57
     inherited
    -1.57
    POSITIVE LOGITS
     Extensions
    1.96
     Properties
    1.95
    Services
    1.88
     Values
    1.87
    SPONSORED
    1.85
     Distance
    1.80
     Summary
    1.79
    Appearance
    1.79
     Migration
    1.78
     Practices
    1.77
    Act Density 0.005%

    No Known Activations