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

    Neuronpedia

    INDEX
    Explanations

    the acronym "lol" in texts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     redress
    -0.80
     Components
    -0.70
     Sinai
    -0.69
     entrusted
    -0.68
     contracted
    -0.67
     distingu
    -0.64
     bearer
    -0.64
    pell
    -0.64
    rament
    -0.64
    venant
    -0.62
    POSITIVE LOGITS
    ipop
    0.92
    cow
    0.91
    ðŁĺ
    0.91
    ita
    0.89
    cats
    0.84
    zers
    0.80
    ghan
    0.78
    !!!!!
    0.75
    arella
    0.75
    laugh
    0.73
    Act Density 0.025%

    No Known Activations