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

    Neuronpedia

    INDEX
    Explanations

    causative language indicating negative consequences or effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cken
    -0.17
    osemite
    -0.16
    coming
    -0.15
    gett
    -0.15
    cke
    -0.15
    elsing
    -0.15
    -Ñı
    -0.14
    ../../../
    -0.14
    gi
    -0.14
    iferay
    -0.14
    POSITIVE LOGITS
    -sdk
    0.15
    ναν
    0.14
    lessly
    0.13
    /ca
    0.13
    fully
    0.13
    nces
    0.13
    lier
    0.13
    .mods
    0.13
    ellation
    0.13
    SD
    0.13
    Act Density 0.038%

    No Known Activations