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

    Neuronpedia

    INDEX
    Explanations

    references to recorded incidents and videos

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.01
    2:0.05
    3:0.20
    4:0.02
    5:0.12
    6:0.02
    7:0.06
    8:0.02
    9:0.03
    10:0.30
    11:0.03
    Negative Logits
    addons
    -2.12
    tools
    -2.11
    awar
    -2.06
    afer
    -2.05
     ));
    -2.02
    aware
    -2.01
    atana
    -2.01
    rawler
    -1.95
    shield
    -1.94
    Rogue
    -1.94
    POSITIVE LOGITS
     conversation
    2.93
     sermon
    2.84
     speeches
    2.81
     voic
    2.68
     conversations
    2.67
     VIDEOS
    2.64
     spontaneous
    2.57
     confession
    2.51
     speech
    2.50
     firsthand
    2.42
    Act Density 0.019%

    No Known Activations