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

    Neuronpedia

    INDEX
    Explanations

    references to financial impacts and economic concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ALSE
    -0.17
    elige
    -0.17
    ãĤĪãģ³
    -0.15
    APTER
    -0.15
    бÑĥдÑĮ
    -0.15
    ILTER
    -0.15
    ILLE
    -0.15
    utto
    -0.15
    SSERT
    -0.15
    аÑĤков
    -0.15
    POSITIVE LOGITS
     v
    0.16
     Roy
    0.14
     c
    0.14
    -↵
    0.14
     the
    0.14
     directly
    0.14
     ench
    0.14
     div
    0.13
    rob
    0.13
     every
    0.13
    Act Density 0.039%

    No Known Activations