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

    Neuronpedia

    INDEX
    Explanations

    phrases conveying significant change or transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mainland
    -0.18
    esso
    -0.16
     policym
    -0.15
    ữ
    -0.15
    undi
    -0.15
    /rfc
    -0.15
    ienza
    -0.15
    гоÑĢ
    -0.15
    intl
    -0.14
    auer
    -0.14
    POSITIVE LOGITS
    tol
    0.16
    eras
    0.16
    copyright
    0.15
    uga
    0.14
    tim
    0.14
    abol
    0.14
    opsis
    0.14
     Ñĩа
    0.13
     ROCK
    0.13
    town
    0.13
    Act Density 0.411%

    No Known Activations