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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "traction" or gaining momentum

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.08
    3:0.06
    4:0.14
    5:0.03
    6:0.04
    7:0.34
    8:0.03
    9:0.04
    10:0.08
    11:0.08
    Negative Logits
    ortality
    -1.71
    iem
    -1.52
    utan
    -1.50
     latitude
    -1.49
    ftime
    -1.45
    RIP
    -1.43
    esthesia
    -1.42
    ige
    -1.37
    ailand
    -1.37
    access
    -1.36
    POSITIVE LOGITS
    soType
    1.66
    pole
    1.57
     polls
    1.42
     unpopular
    1.41
     chorus
    1.40
     Conspiracy
    1.30
     rpm
    1.28
     intrig
    1.26
    kamp
    1.25
     roadside
    1.25
    Act Density 0.001%

    No Known Activations