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

    Neuronpedia

    INDEX
    Explanations

    references to specific metrics or measurements in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĢап
    -0.15
    avana
    -0.15
    ма
    -0.15
     SAS
    -0.14
    PropertyDescriptor
    -0.14
     ///</
    -0.14
    ORIZED
    -0.14
    ienie
    -0.14
    pons
    -0.14
    اÙĩد
    -0.14
    POSITIVE LOGITS
     Sense
    0.35
    Sense
    0.29
     scri
    0.23
     sense
    0.23
     CMP
    0.22
     ru
    0.21
    NSE
    0.21
     Ru
    0.20
    Ru
    0.20
    CMP
    0.19
    Act Density 0.010%

    No Known Activations