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

    Neuronpedia

    INDEX
    Explanations

    elements of humor and critique in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    μοÏħ
    -0.15
    lei
    -0.14
    @student
    -0.14
    à¹īà¸ĩ
    -0.14
    StringLength
    -0.14
    еком
    -0.14
    è§Ĵ
    -0.14
     aray
    -0.13
     ÑĦоÑĢма
    -0.13
    _fonts
    -0.13
    POSITIVE LOGITS
     sometimes
    0.48
    sometimes
    0.40
     occasionally
    0.37
     Sometimes
    0.36
     certain
    0.35
    Sometimes
    0.35
    ometimes
    0.32
     certains
    0.30
     some
    0.29
     иногда
    0.28
    Act Density 0.110%

    No Known Activations