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

    Neuronpedia

    INDEX
    Explanations

    references to academic institutions and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utow
    -0.18
    FROM
    -0.16
    OURS
    -0.16
    dez
    -0.14
    eyh
    -0.14
    INGS
    -0.14
    tings
    -0.14
     davon
    -0.14
    ÅĤ
    -0.13
    dest
    -0.13
    POSITIVE LOGITS
     Against
    0.22
     foe
    0.20
     fur
    0.20
     For
    0.19
    (s
    0.16
     Adv
    0.16
     Without
    0.16
     Yourself
    0.16
     fuer
    0.16
    /List
    0.15
    Act Density 0.141%

    No Known Activations