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

    Neuronpedia

    INDEX
    Explanations

    themes related to choice and representation in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģ«ãģĭ
    -0.16
    оза
    -0.15
     Guil
    -0.15
    QUIRED
    -0.15
    ucch
    -0.15
    εÏĤ
    -0.15
    aded
    -0.14
    Ïģκ
    -0.14
    reme
    -0.14
    ADING
    -0.14
    POSITIVE LOGITS
     Wis
    0.17
     Lyons
    0.15
    apis
    0.14
    ENCIL
    0.14
    ZN
    0.14
    ILog
    0.14
     TimeUnit
    0.14
    cop
    0.13
     Yah
    0.13
     Scr
    0.13
    Act Density 0.209%

    No Known Activations