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

    Neuronpedia

    INDEX
    Explanations

    references to personal experiences and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ourselves
    -0.16
    elsing
    -0.15
    á»ĵ
    -0.15
    дем
    -0.15
    Ñģим
    -0.15
    retch
    -0.14
    unsch
    -0.14
    olet
    -0.14
    olas
    -0.14
    ابط
    -0.14
    POSITIVE LOGITS
     whereas
    0.17
     himself
    0.17
     garage
    0.15
     herself
    0.14
     constituents
    0.14
     Garage
    0.14
    mant
    0.13
    avad
    0.13
     rig
    0.13
     hed
    0.13
    Act Density 0.393%

    No Known Activations