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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "strict" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aling
    -0.16
    airo
    -0.15
     Prest
    -0.14
    aram
    -0.14
     konkrét
    -0.14
    ='".
    -0.14
    conciliation
    -0.14
    Ñĩика
    -0.13
    brig
    -0.13
    opathy
    -0.13
    POSITIVE LOGITS
    ures
    0.32
    est
    0.30
    ness
    0.25
    /loose
    0.23
     adherence
    0.22
    ured
    0.21
    uring
    0.19
    ement
    0.19
     Strict
    0.18
    å·±
    0.18
    Act Density 0.022%

    No Known Activations