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

    Neuronpedia

    INDEX
    Explanations

    calls to action or imperative statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.06
    3:0.08
    4:0.15
    5:0.04
    6:0.05
    7:0.27
    8:0.04
    9:0.05
    10:0.09
    11:0.06
    Negative Logits
     incurred
    -1.51
    bucks
    -1.49
    ithing
    -1.48
     incur
    -1.46
    ascus
    -1.46
     charging
    -1.45
    aeus
    -1.44
    imgur
    -1.44
     ---------
    -1.44
    cong
    -1.42
    POSITIVE LOGITS
     notions
    2.19
     realities
    1.81
     nostalgia
    1.81
     concepts
    1.78
     interpretations
    1.71
     metaphors
    1.68
     prag
    1.62
     notion
    1.62
     simplistic
    1.59
     philosophies
    1.58
    Act Density 0.000%

    No Known Activations