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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "never"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.17
    éĺħ
    -0.17
    tÃŃ
    -0.15
    ection
    -0.15
    Torrent
    -0.14
    ån
    -0.14
    aliyet
    -0.14
    nodoc
    -0.14
    oa
    -0.14
    arters
    -0.14
    POSITIVE LOGITS
    theless
    0.36
    -ending
    0.31
    ending
    0.20
    -before
    0.19
    -ever
    0.17
    th
    0.17
     ending
    0.17
    ed
    0.16
    never
    0.15
    ceased
    0.15
    Act Density 0.042%

    No Known Activations