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

    Neuronpedia

    INDEX
    Explanations

    demonstrative pronouns and their connections to context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erm
    -0.19
     above
    -0.16
     Wright
    -0.15
    above
    -0.15
    enci
    -0.15
    ischen
    -0.14
    rap
    -0.14
    vice
    -0.14
    akh
    -0.14
    asi
    -0.14
    POSITIVE LOGITS
    iž
    0.17
    ROWSER
    0.15
    esser
    0.14
     ê·¸ê²ĥ
    0.14
    atz
    0.14
    CppObject
    0.14
    nist
    0.14
    ENTITY
    0.14
     onu
    0.13
    Dispatch
    0.13
    Act Density 0.177%

    No Known Activations