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

    Neuronpedia

    INDEX
    Explanations

    expressions related to enjoyment and positive experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asio
    -0.15
    лоп
    -0.14
    orde
    -0.14
    /DD
    -0.14
    ernote
    -0.14
    mesinin
    -0.14
    /Dk
    -0.13
     Boeh
    -0.13
    echan
    -0.13
    tesy
    -0.13
    POSITIVE LOGITS
     cool
    1.06
     Cool
    0.90
    cool
    0.86
    Cool
    0.85
     coolest
    0.68
     cooler
    0.68
     neat
    0.63
     cooled
    0.52
     Cooler
    0.52
     cooling
    0.51
    Act Density 0.475%

    No Known Activations