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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "adjust" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucle
    -0.15
    uels
    -0.15
     republika
    -0.14
    osemite
    -0.14
    onto
    -0.14
    Ãłn
    -0.14
     sever
    -0.14
     Jaune
    -0.14
    iske
    -0.14
    486
    -0.14
    POSITIVE LOGITS
    rit
    0.15
    arse
    0.15
    abel
    0.15
    halb
    0.15
    ingo
    0.15
    imeo
    0.14
    mir
    0.14
    ansson
    0.14
    109
    0.13
    nya
    0.13
    Act Density 0.015%

    No Known Activations