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

    Neuronpedia

    INDEX
    Explanations

    specific Swedish characters and linguistic features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ì²Ń
    -0.15
    ëŀĺ
    -0.15
    dech
    -0.15
    ous
    -0.14
    /state
    -0.14
    گر
    -0.14
     jde
    -0.14
    fore
    -0.14
    ÄŁa
    -0.14
    ago
    -0.14
    POSITIVE LOGITS
    estr
    0.17
    ican
    0.16
    eker
    0.16
    quist
    0.16
    eature
    0.15
    eps
    0.15
    GRID
    0.15
    ött
    0.15
    aan
    0.15
    erox
    0.15
    Act Density 0.060%

    No Known Activations