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

    Neuronpedia

    INDEX
    Explanations

    specific morphological components or endings of words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imedia
    -0.16
    arella
    -0.15
    brick
    -0.15
    esome
    -0.15
    ibrate
    -0.15
    edom
    -0.15
    à¤ľà¤¨
    -0.15
    ÑĢÑĥн
    -0.15
    deaux
    -0.14
    icient
    -0.14
    POSITIVE LOGITS
    itre
    0.15
    ิยม
    0.14
    ÏĦαÏĤ
    0.14
    Ĥæķ°
    0.14
    etre
    0.14
    gba
    0.13
    ry
    0.13
     Verd
    0.13
    ort
    0.13
     intending
    0.13
    Act Density 0.504%

    No Known Activations