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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating social interactions or emotional relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     مرئيه
    -0.61
     Ведь
    -0.51
     Нам
    -0.49
    initComponents
    -0.48
     tali
    -0.47
    ोजना
    -0.46
    ELEMENTS
    -0.46
    consulté
    -0.46
     propOrder
    -0.46
    TagHelper
    -0.45
    POSITIVE LOGITS
    不管是
    1.42
     regardless
    1.40
    regardless
    1.40
    无论是
    1.34
     whether
    1.32
     including
    1.30
    whether
    1.27
    不论
    1.23
    無論
    1.21
     irrespective
    1.21
    Act Density 0.516%

    No Known Activations