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

    Neuronpedia

    INDEX
    Explanations

    attributes and properties defined in XML-like structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    елиÑĩ
    -0.15
    antt
    -0.15
     Mil
    -0.15
    ë¦Ħ
    -0.15
    erd
    -0.14
    cesso
    -0.14
    orrent
    -0.14
    овиÑĩ
    -0.14
     Incontri
    -0.14
     ex
    -0.13
    POSITIVE LOGITS
     tel
    0.15
    tel
    0.15
    ingo
    0.15
    ég
    0.15
    oldt
    0.14
    imas
    0.14
    ega
    0.14
    ³
    0.14
    ruh
    0.14
    WH
    0.13
    Act Density 0.002%

    No Known Activations