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

    Neuronpedia

    INDEX
    Explanations

    dates and events related to specific creations or releases

    oai_token-act-pair · gpt-3.5-turbo

    phrases or words indicating the creation or establishment of entities or works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thinner
    -0.74
     mail
    -0.73
     mort
    -0.72
     reflex
    -0.72
     attrition
    -0.71
     tissue
    -0.70
     contingency
    -0.70
     nevertheless
    -0.70
     diversion
    -0.68
     sever
    -0.68
    POSITIVE LOGITS
     Created
    2.89
     Known
    2.33
     Located
    2.03
     Released
    1.97
     Designed
    1.96
     Called
    1.90
     Built
    1.88
    Known
    1.79
    Created
    1.77
     Named
    1.75
    Act Density 0.054%

    No Known Activations