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

    Neuronpedia

    INDEX
    Explanations

    Grammar and word usage

    np_max-act · gemini-2.0-flash

    active and passive voice constructions in sentences.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     territory
    -0.07
    osal
    -0.06
    zim
    -0.06
    (api
    -0.06
    etch
    -0.06
    cının
    -0.06
    sko
    -0.06
     reasonably
    -0.06
    階
    -0.06
     oral
    -0.06
    POSITIVE LOGITS
     Zhang
    0.07
    ICAST
    0.07
    .STATE
    0.07
    onor
    0.07
    vature
    0.07
     نع
    0.06
    _]
    0.06
    ijing
    0.06
     mf
    0.06
    .sqlite
    0.06
    Act Density 0.038%

    No Known Activations