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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "when" followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve conditional or situational "when" statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pledge
    -0.68
    FORE
    -0.67
     ¶
    -0.66
    lihood
    -0.66
     Language
    -0.66
     Dragonbound
    -0.64
    ulous
    -0.62
     warranty
    -0.61
    PsyNetMessage
    -0.60
     Reasons
    -0.59
    POSITIVE LOGITS
     eaten
    1.46
     viewed
    1.43
     handled
    1.39
     taken
    1.37
     placed
    1.35
     ingested
    1.33
     consumed
    1.29
     subjected
    1.28
     executed
    1.27
     examined
    1.27
    Act Density 0.146%

    No Known Activations