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

    Neuronpedia

    INDEX
    Explanations

    references to specific items or concepts, particularly those that are emphasized or presented in relation to the context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tap
    -0.16
    ovo
    -0.15
     this
    -0.14
    jin
    -0.14
    å¦Ĥä¸ĭ
    -0.13
     Cast
    -0.13
    rine
    -0.13
     ÑįÑĤо
    -0.13
    resolver
    -0.13
     This
    -0.12
    POSITIVE LOGITS
    /th
    0.27
     particular
    0.19
    zelf
    0.19
    /her
    0.18
    curity
    0.18
    ìłĢ
    0.16
    że
    0.16
    chy
    0.16
    iner
    0.15
    ãĤĪãģĨãģª
    0.15
    Act Density 0.445%

    No Known Activations