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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate action and engagement with content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sát
    -0.15
    anh
    -0.14
    ongan
    -0.13
    aea
    -0.13
    .aspx
    -0.13
    getc
    -0.13
    irus
    -0.13
    hint
    -0.13
    .cy
    -0.13
     ê²½ìłľ
    -0.13
    POSITIVE LOGITS
     AFTER
    0.20
     jump
    0.20
    Embedded
    0.20
     embed
    0.19
     after
    0.18
     Embedded
    0.18
     embedded
    0.18
     below
    0.17
    Embed
    0.17
    umo
    0.16
    Act Density 0.057%

    No Known Activations