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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a call to action or recruitment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.03
    2:0.07
    3:0.06
    4:0.08
    5:0.03
    6:0.04
    7:0.40
    8:0.05
    9:0.04
    10:0.07
    11:0.06
    Negative Logits
    width
    -1.79
    iveness
    -1.62
    mentation
    -1.60
    ffect
    -1.51
    rats
    -1.50
    teness
    -1.49
     superiority
    -1.48
    expression
    -1.47
    hesion
    -1.46
     outcome
    -1.45
    POSITIVE LOGITS
    Guard
    1.54
    uga
    1.52
    liga
    1.40
    Nob
    1.39
    yi
    1.38
     Indra
    1.37
     register
    1.36
     laundry
    1.36
    HI
    1.34
    DragonMagazine
    1.33
    Act Density 0.002%

    No Known Activations