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

    Neuronpedia

    INDEX
    Explanations

    phrases and concepts related to evaluation and significance in contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )((((
    -0.15
    plnÄĽ
    -0.14
    clus
    -0.14
    artin
    -0.13
    quez
    -0.13
    bla
    -0.13
    kara
    -0.13
    анÑģи
    -0.13
    ¤ëĭ¤
    -0.13
    elda
    -0.12
    POSITIVE LOGITS
     recent
    0.16
     recently
    0.14
    recent
    0.13
     же
    0.13
    Recently
    0.12
     additional
    0.12
    anje
    0.12
    atÃŃm
    0.12
     hypoc
    0.12
     &
    0.12
    Act Density 0.024%

    No Known Activations