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

    Neuronpedia

    INDEX
    Explanations

    numbers and ratings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.23
    1:0.06
    2:0.07
    3:0.06
    4:0.03
    5:0.05
    6:0.07
    7:0.01
    8:0.11
    9:0.10
    10:0.09
    11:0.06
    Negative Logits
    hap
    -1.64
    bum
    -1.61
    jen
    -1.57
    minist
    -1.56
    zeb
    -1.55
    misc
    -1.50
    voy
    -1.48
    ogh
    -1.45
    stim
    -1.45
    bis
    -1.45
    POSITIVE LOGITS
     srfAttach
    1.81
     homegrown
    1.46
     �
    1.46
     ­
    1.37
    ilingual
    1.37
     •
    1.33
     shoots
    1.33
    【
    1.32
     English
    1.31
     Firearms
    1.29
    Act Density 0.001%

    No Known Activations