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

    Neuronpedia

    INDEX
    Explanations

    special characters and non-standard symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.01
    2:0.12
    3:0.07
    4:0.05
    5:0.02
    6:0.24
    7:0.15
    8:0.04
    9:0.04
    10:0.07
    11:0.07
    Negative Logits
    undown
    -1.58
     dictators
    -1.37
    aution
    -1.35
     Scully
    -1.34
     distraction
    -1.32
     uncond
    -1.28
     confir
    -1.23
     pestic
    -1.23
     conclud
    -1.22
     Disclosure
    -1.22
    POSITIVE LOGITS
    �
    1.70
    �
    1.57
    Eastern
    1.50
    ua
    1.39
    ּ
    1.38
    �醒
    1.37
    �
    1.36
    EStream
    1.35
    �
    1.32
    �
    1.30
    Act Density 0.002%

    No Known Activations