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

    Neuronpedia

    INDEX
    Explanations

    expressions of happiness or positive emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ɵ
    -0.15
    .aspx
    -0.14
    ROP
    -0.14
    åĥıæĺ¯
    -0.14
    935
    -0.13
     pl
    -0.13
    ood
    -0.13
    æŁı
    -0.13
    orpion
    -0.13
    wers
    -0.13
    POSITIVE LOGITS
    ä¹İ
    0.18
    abar
    0.14
     disappe
    0.14
    kul
    0.14
    ozem
    0.14
    bach
    0.14
    .emf
    0.14
    ÅĻÃŃž
    0.14
    prox
    0.14
    /os
    0.14
    Act Density 0.032%

    No Known Activations