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

    Neuronpedia

    INDEX
    Explanations

    phrases that signify examining or discussing topics in detail

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pu
    -0.15
    amac
    -0.14
    пи
    -0.14
    .camel
    -0.13
    jong
    -0.13
    retty
    -0.13
    pagen
    -0.13
    mere
    -0.13
    lag
    -0.13
    oin
    -0.12
    POSITIVE LOGITS
     briefly
    0.21
     shall
    0.19
    ä¸Ģä¸ĭ
    0.18
     Shall
    0.17
    shall
    0.17
    åIJ§
    0.16
     ourselves
    0.15
     SHALL
    0.15
    .scalablytyped
    0.15
    brief
    0.15
    Act Density 0.122%

    No Known Activations