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

    Neuronpedia

    INDEX
    Explanations

    second-person pronouns and related context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adel
    -0.16
    ower
    -0.15
    éc
    -0.14
    urn
    -0.14
    stre
    -0.14
    enn
    -0.14
    mage
    -0.13
    agos
    -0.13
    ulse
    -0.13
    nof
    -0.13
    POSITIVE LOGITS
     must
    0.17
     should
    0.17
     can
    0.16
    ãģıãĤĵ
    0.15
    å¢
    0.15
     SHOULD
    0.15
     shouldn
    0.14
    天åłĤ
    0.14
    rending
    0.14
     shall
    0.14
    Act Density 0.066%

    No Known Activations