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

    Neuronpedia

    INDEX
    Explanations

    instances of actions that involve movement or physical presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tring
    -0.16
    vie
    -0.16
    roti
    -0.16
    898
    -0.15
    utsch
    -0.15
    lavÃŃ
    -0.14
    ÐĬ
    -0.14
    htub
    -0.14
    UTE
    -0.14
     Straw
    -0.13
    POSITIVE LOGITS
     arrival
    0.17
     reap
    0.17
     brought
    0.16
     bring
    0.15
    246
    0.15
    Bring
    0.15
    ponent
    0.15
    Č
    0.15
    inos
    0.15
     presence
    0.15
    Act Density 0.332%

    No Known Activations