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

    Neuronpedia

    INDEX
    Explanations

    terms related to linguistics and language studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adero
    -0.15
    ç·Ĵ
    -0.15
     Farr
    -0.15
     Dud
    -0.15
    clarations
    -0.14
    ÏģÏį
    -0.14
     Dudley
    -0.14
    //**↵
    -0.14
    ãĤ§
    -0.14
    ologue
    -0.14
    POSITIVE LOGITS
    istics
    0.33
     franca
    0.21
    istically
    0.18
    istic
    0.18
    иÑģк
    0.17
    aggio
    0.17
    -cultural
    0.17
     زد
    0.16
    auge
    0.16
     Ling
    0.16
    Act Density 0.006%

    No Known Activations