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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the verb "do" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.09
    2:0.04
    3:0.03
    4:0.03
    5:0.23
    6:0.03
    7:0.04
    8:0.15
    9:0.05
    10:0.10
    11:0.07
    Negative Logits
     sqor
    -1.67
     UCS
    -1.52
    racuse
    -1.48
    assis
    -1.47
    neum
    -1.45
    member
    -1.45
    male
    -1.44
    inian
    -1.43
    phia
    -1.42
     agrees
    -1.41
    POSITIVE LOGITS
     deeds
    1.75
     advoc
    1.59
     routines
    1.52
     shampoo
    1.51
    intent
    1.50
    soDeliveryDate
    1.45
    ────
    1.44
    ageddon
    1.43
    wcsstore
    1.43
     deed
    1.43
    Act Density 0.033%

    No Known Activations