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

    Neuronpedia

    INDEX
    Explanations

    emotional expressions and relationships in personal narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     once
    -0.26
    once
    -0.23
    Once
    -0.21
     Once
    -0.20
     wherever
    -0.16
    etto
    -0.16
    amma
    -0.15
    _once
    -0.15
    aga
    -0.14
    antan
    -0.14
    POSITIVE LOGITS
     when
    0.24
     followed
    0.23
    when
    0.21
    .when
    0.20
     quando
    0.19
     gdy
    0.18
     cuando
    0.17
     until
    0.17
     عÙĨدÙħا
    0.17
     When
    0.17
    Act Density 0.014%

    No Known Activations