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

    Neuronpedia

    INDEX
    Explanations

    phrases or words related to emphasis or importance

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating certainty, commonality, or ongoing situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Doing
    -0.76
    ivating
    -0.68
    izont
    -0.67
    YING
    -0.67
     Writing
    -0.66
     Aware
    -0.66
     Saying
    -0.65
    onding
    -0.65
     Talking
    -0.64
    arter
    -0.64
    POSITIVE LOGITS
     resembled
    1.11
     existed
    1.11
     happened
    1.09
     resembles
    1.07
     coincides
    1.04
     happens
    1.04
     belonged
    1.04
     resided
    1.02
     derives
    1.01
     earns
    1.00
    Act Density 0.225%

    No Known Activations