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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "ever," particularly in varying contexts that emphasize its significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ofire
    -0.17
    ively
    -0.16
    exter
    -0.15
    ikal
    -0.15
    ulary
    -0.15
    ilver
    -0.14
    ledon
    -0.14
    .scalablytyped
    -0.14
    ardin
    -0.14
    êu
    -0.14
    POSITIVE LOGITS
    greens
    0.28
    green
    0.24
    theless
    0.24
    -ending
    0.19
    mind
    0.18
    lasting
    0.17
    -present
    0.17
    adium
    0.17
    olls
    0.15
    more
    0.15
    Act Density 0.061%

    No Known Activations