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

    Neuronpedia

    INDEX
    Explanations

    nouns or phrases that indicate relationships or affiliations, particularly those involving descriptors of individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     киÑģл
    -0.17
    ment
    -0.16
    ufac
    -0.15
    kov
    -0.15
    Äĥn
    -0.14
    ars
    -0.14
     Serializable
    -0.14
    åĪ»
    -0.14
    تÙĨ
    -0.14
    usc
    -0.13
    POSITIVE LOGITS
    DataTask
    0.16
    .setPrototypeOf
    0.15
    uitka
    0.14
    RICT
    0.14
    DTD
    0.14
    代
    0.14
     Suc
    0.14
    ransition
    0.14
     cáºŃn
    0.14
    ober
    0.13
    Act Density 0.016%

    No Known Activations