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

    Neuronpedia

    INDEX
    Explanations

    instances of imperative verbs or commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.07
    2:0.07
    3:0.08
    4:0.10
    5:0.10
    6:0.07
    7:0.08
    8:0.08
    9:0.08
    10:0.08
    11:0.08
    Negative Logits
     BASE
    -2.33
    mort
    -2.09
    phia
    -2.05
    orld
    -2.03
    アル
    -1.97
     Californ
    -1.94
    anmar
    -1.91
    assic
    -1.90
    atom
    -1.88
    ankind
    -1.85
    POSITIVE LOGITS
     strides
    2.04
     ✔
    2.01
     endorsement
    1.97
     Posted
    1.97
     Profile
    1.96
    ulpt
    1.96
     leaflets
    1.94
     Warranty
    1.93
     Shine
    1.92
     playable
    1.92
    Act Density 0.000%

    No Known Activations