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

    Neuronpedia

    INDEX
    Explanations

    critical commentary on societal or political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.14
    2:0.14
    3:0.03
    4:0.02
    5:0.04
    6:0.07
    7:0.16
    8:0.15
    9:0.06
    10:0.06
    11:0.04
    Negative Logits
     *)
    -1.27
     Malfoy
    -1.18
     Hug
    -1.17
     «
    -1.16
     Belg
    -1.14
     Haf
    -1.12
     Wing
    -1.10
    ‎
    -1.10
     Hung
    -1.08
    !)
    -1.07
    POSITIVE LOGITS
    etheless
    1.56
    omo
    1.43
    erial
    1.42
    azeera
    1.42
    ital
    1.39
    omal
    1.35
    anyon
    1.33
    ritional
    1.31
    emale
    1.30
    oser
    1.29
    Act Density 0.140%

    No Known Activations