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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate significant events or milestones in sports or entertainment contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     beginnings
    -0.15
    ÄĽr
    -0.14
    elin
    -0.14
    .acquire
    -0.13
    ä¸Ģä¸ĭ
    -0.13
    erate
    -0.13
    ntl
    -0.13
    ollect
    -0.13
     zwar
    -0.13
     Samurai
    -0.13
    POSITIVE LOGITS
    ClassLoader
    0.15
    xo
    0.15
    hawks
    0.14
     trục
    0.14
     yine
    0.14
    apiro
    0.14
     Zub
    0.14
     Hoff
    0.14
    hawk
    0.14
    jad
    0.14
    Act Density 0.241%

    No Known Activations