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

    Neuronpedia

    INDEX
    Explanations

    future events or plans mentioned in a document

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    wright
    -0.93
    lang
    -0.84
    tics
    -0.81
    isters
    -0.79
    speak
    -0.78
    then
    -0.78
    ochet
    -0.77
    puters
    -0.76
    rea
    -0.76
    sometimes
    -0.75
    POSITIVE LOGITS
     iteration
    1.09
     edition
    1.06
     installment
    1.06
     announcement
    1.02
     batch
    0.97
     onslaught
    0.96
     confrontation
    0.96
     showdown
    0.96
     spate
    0.93
     arrival
    0.92
    Act Density 1.480%

    No Known Activations