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

    Neuronpedia

    INDEX
    Explanations

    active verbs and phrases indicating ongoing actions or developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.02
    2:0.06
    3:0.12
    4:0.02
    5:0.05
    6:0.02
    7:0.03
    8:0.02
    9:0.02
    10:0.50
    11:0.02
    Negative Logits
     Flavoring
    -2.23
     agreeing
    -2.21
     victory
    -2.12
    reements
    -2.01
    joining
    -1.97
     previous
    -1.96
    iphany
    -1.96
     concluding
    -1.96
     plateau
    -1.94
    History
    -1.94
    POSITIVE LOGITS
    itored
    2.81
     monitored
    2.56
     investigated
    2.29
    farious
    2.29
     prosec
    2.24
     tested
    2.16
     harshly
    2.13
     handled
    2.12
     scrutin
    2.11
     discussed
    2.08
    Act Density 0.118%

    No Known Activations