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

    Neuronpedia

    INDEX
    Explanations

    variations of the verb "to be" and related auxiliary verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.02
    2:0.17
    3:0.12
    4:0.02
    5:0.02
    6:0.07
    7:0.04
    8:0.07
    9:0.12
    10:0.12
    11:0.17
    Negative Logits
    gencies
    -1.03
     Jackets
    -0.96
    Avg
    -0.94
    anan
    -0.93
    ulner
    -0.87
     Haz
    -0.83
    elin
    -0.81
    onite
    -0.81
    erb
    -0.79
    notations
    -0.78
    POSITIVE LOGITS
     anymore
    1.82
     nor
    1.52
     anytime
    1.11
     anything
    1.09
     anywhere
    1.08
     any
    1.06
     altogether
    1.03
     anyone
    1.02
    yet
    0.99
     yet
    0.95
    Act Density 0.019%

    No Known Activations