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

    Neuronpedia

    INDEX
    Explanations

    expressions of trust and reliance on personal judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.02
    2:0.06
    3:0.08
    4:0.15
    5:0.04
    6:0.04
    7:0.24
    8:0.05
    9:0.04
    10:0.11
    11:0.07
    Negative Logits
    uble
    -1.92
     deficit
    -1.49
    naire
    -1.44
     pools
    -1.43
     pits
    -1.42
     deficits
    -1.37
     complexes
    -1.33
     spectator
    -1.33
    etter
    -1.30
     reckoning
    -1.29
    POSITIVE LOGITS
     Instruct
    1.51
     Corsair
    1.49
     Attribution
    1.43
     sounded
    1.43
     preach
    1.34
    elight
    1.33
    wt
    1.31
     hearty
    1.29
     louder
    1.27
    nos
    1.27
    Act Density 0.000%

    No Known Activations