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

    Neuronpedia

    INDEX
    Explanations

    the word "usually" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating common or typical behaviors and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Agenda
    -0.75
     Orchestra
    -0.68
     Kut
    -0.67
    banks
    -0.67
     Kob
    -0.66
     Tag
    -0.66
     Sel
    -0.65
     Mark
    -0.65
     Shard
    -0.65
     Abdullah
    -0.64
    POSITIVE LOGITS
    entimes
    1.10
     overlooked
    0.85
     regarded
    0.84
     suspects
    0.81
     frowned
    0.79
     relegated
    0.78
     reserved
    0.77
     referred
    0.76
     encountered
    0.75
     grav
    0.75
    Act Density 0.024%

    No Known Activations