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

    Neuronpedia

    INDEX
    Explanations

    sentiments related to technology and digital interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.12
    1:0.03
    2:0.16
    3:0.05
    4:0.05
    5:0.08
    6:0.12
    7:0.05
    8:0.06
    9:0.17
    10:0.02
    11:0.03
    Negative Logits
     Baghd
    -3.74
     Abel
    -3.49
     bunker
    -3.33
     Bunker
    -3.31
    etheus
    -3.29
     Prometheus
    -3.29
     Boone
    -3.25
     constitu
    -3.15
     semin
    -3.12
     Columb
    -3.11
    POSITIVE LOGITS
    Touch
    7.71
     Touch
    7.42
    touch
    6.80
     touch
    5.84
     tactile
    5.28
     touching
    5.26
     touches
    5.18
     touchscreen
    5.06
     fingert
    4.77
     gestures
    4.75
    Act Density 0.018%

    No Known Activations