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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing the quality of something

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    mit
    -0.66
    orate
    -0.64
    wan
    -0.63
    roud
    -0.63
    rift
    -0.63
    leeve
    -0.62
    ][/
    -0.62
    ould
    -0.62
    acker
    -0.61
    idates
    -0.61
    POSITIVE LOGITS
     ones
    0.95
     namely
    0.89
    those
    0.87
     those
    0.81
     ours
    0.68
    including
    0.68
     including
    0.67
     Blaster
    0.65
     Including
    0.64
     weddings
    0.62
    Act Density 4.861%

    No Known Activations