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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "under" and its variations, indicating a focus on contexts related to limitations or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oine
    -0.16
    are
    -0.16
    antal
    -0.14
    ching
    -0.14
    дем
    -0.14
    /cms
    -0.13
    ilis
    -0.13
    otas
    -0.13
    _PUS
    -0.13
    anz
    -0.13
    POSITIVE LOGITS
    neath
    0.25
    whel
    0.19
    sea
    0.18
     conditions
    0.17
    whelming
    0.17
     circumstances
    0.16
    lain
    0.15
    lie
    0.15
    ling
    0.14
    lug
    0.14
    Act Density 0.065%

    No Known Activations