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

    Neuronpedia

    INDEX
    Explanations

    verbs and actions related to communication, reporting, and addressing complexities or changes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.04
    2:0.12
    3:0.03
    4:0.02
    5:0.03
    6:0.06
    7:0.09
    8:0.21
    9:0.08
    10:0.08
    11:0.18
    Negative Logits
    の魔
    -1.30
     glim
    -1.21
    FORE
    -1.07
     Christy
    -1.05
    ACP
    -1.02
     proudly
    -1.01
     proceeded
    -1.01
     unanimously
    -1.00
    accompanied
    -1.00
     Leia
    -0.99
    POSITIVE LOGITS
    cation
    1.58
     altogether
    1.49
     anymore
    1.41
     pitfalls
    1.37
    traditional
    1.30
     nor
    1.20
    ratch
    1.17
    usive
    1.17
     traps
    1.15
    cuts
    1.15
    Act Density 0.043%

    No Known Activations