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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing control or influence over circumstances and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /GPL
    -0.17
    anza
    -0.15
    оказ
    -0.15
    .scalablytyped
    -0.15
    éIJ
    -0.15
    ãĥ¥
    -0.14
    )throws
    -0.14
    onis
    -0.14
    anz
    -0.14
    ogne
    -0.14
    POSITIVE LOGITS
     Lin
    0.15
     myself
    0.15
     Guth
    0.14
    Embedded
    0.14
    çĦ¼
    0.13
     Abbott
    0.13
     Saunders
    0.13
    unan
    0.13
    ìķ¼
    0.13
     Ames
    0.13
    Act Density 0.134%

    No Known Activations