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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating something is permanent or enduring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iston
    -0.20
    692
    -0.17
     Spor
    -0.15
     bordel
    -0.14
     Wick
    -0.14
    ivr
    -0.14
     Vere
    -0.13
    ãĥĸãĥª
    -0.13
    586
    -0.13
     runnable
    -0.13
    POSITIVE LOGITS
     stay
    1.14
     stays
    1.03
     Stay
    1.02
     stayed
    1.01
     staying
    0.99
    Stay
    0.96
    stay
    0.95
    -st
    0.49
     remained
    0.45
     remain
    0.44
    Act Density 0.242%

    No Known Activations