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

    Neuronpedia

    INDEX
    Explanations

    references to specific publications or archives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.33
    1:0.02
    2:0.01
    3:0.07
    4:0.09
    5:0.04
    6:0.03
    7:0.01
    8:0.28
    9:0.05
    10:0.01
    11:0.01
    Negative Logits
     handshake
    -1.99
     passwords
    -1.69
     hugs
    -1.63
     pledges
    -1.60
     selfies
    -1.59
    istor
    -1.59
     answers
    -1.58
     behaviours
    -1.58
     resumes
    -1.55
     scaling
    -1.53
    POSITIVE LOGITS
     Canyon
    1.57
     Rim
    1.57
    ribune
    1.54
     Zone
    1.53
    Rated
    1.49
     Alley
    1.48
    Ble
    1.47
    idates
    1.45
    rica
    1.42
     Slam
    1.40
    Act Density 0.000%

    No Known Activations