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

    Neuronpedia

    INDEX
    Explanations

    colons followed by statements or quotes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.17
    3:0.06
    4:0.13
    5:0.02
    6:0.04
    7:0.16
    8:0.05
    9:0.04
    10:0.08
    11:0.15
    Negative Logits
     Surveillance
    -1.44
     Rider
    -1.44
    crime
    -1.37
    licensed
    -1.36
     steroids
    -1.29
     sweats
    -1.29
     taxis
    -1.29
     ordinances
    -1.27
     surveillance
    -1.27
     killer
    -1.26
    POSITIVE LOGITS
    rief
    1.72
    tions
    1.69
    hesis
    1.67
    etus
    1.64
    enario
    1.50
    enture
    1.48
    llo
    1.48
     objection
    1.47
     congress
    1.47
     podium
    1.46
    Act Density 0.001%

    No Known Activations