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

    Neuronpedia

    INDEX
    Explanations

    expressions of positive sentiment or affection towards people, objects, or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stav
    -0.16
    elles
    -0.15
    apur
    -0.15
    -uri
    -0.14
     DY
    -0.14
    ĵ¨
    -0.14
    arkan
    -0.14
    IEW
    -0.14
    rices
    -0.14
    .dy
    -0.13
    POSITIVE LOGITS
    asha
    0.18
    ester
    0.16
    able
    0.15
     overall
    0.15
    olio
    0.15
    olt
    0.15
    olie
    0.14
    -Ñģ
    0.14
    acker
    0.14
    DET
    0.14
    Act Density 0.067%

    No Known Activations