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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant events or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to significant actions and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sleeps
    -0.76
    tains
    -0.64
     waits
    -0.63
    Pros
    -0.62
     è£ıè
    -0.62
     Uses
    -0.60
     resides
    -0.59
     craw
    -0.59
     likes
    -0.59
    hands
    -0.58
    POSITIVE LOGITS
     illustrate
    1.53
     underscore
    1.46
     demonstrate
    1.38
     indicate
    1.38
     remind
    1.34
     imply
    1.33
     undermine
    1.31
     signify
    1.29
     reinforce
    1.28
     constitute
    1.27
    Act Density 0.371%

    No Known Activations