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

    Neuronpedia

    INDEX
    Explanations

    the word "push" in a variety of contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to pressure or movement in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Standards
    -0.67
     Monstrous
    -0.66
     ancest
    -0.65
     HAL
    -0.60
     Principles
    -0.59
     Lak
    -0.58
     Principal
    -0.57
     constitu
    -0.57
     Rica
    -0.57
     Lebanese
    -0.56
    POSITIVE LOGITS
    back
    1.21
    backs
    1.20
    down
    1.14
    over
    1.08
    away
    1.07
    ups
    1.04
    downs
    1.04
    aways
    1.02
    athon
    1.02
    up
    1.01
    Act Density 0.304%

    No Known Activations