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

    Neuronpedia

    INDEX
    Explanations

    references to interpersonal connections and dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iper
    -0.17
     Twe
    -0.17
    arn
    -0.15
    oro
    -0.15
    etsk
    -0.14
    wa
    -0.14
    irc
    -0.14
    izm
    -0.14
    aggi
    -0.14
    wan
    -0.14
    POSITIVE LOGITS
    æĿ¥è¯´
    0.26
    è¿Ļæĺ¯
    0.20
    tridge
    0.16
    ÑĪло
    0.15
    venes
    0.15
    oten
    0.14
    ombine
    0.14
    NECT
    0.14
    istrator
    0.14
    gnu
    0.14
    Act Density 0.075%

    No Known Activations