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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating variability or options available within context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stuff
    -0.16
    pper
    -0.14
    ste
    -0.14
    pe
    -0.14
     Hud
    -0.14
    akeup
    -0.14
    ocker
    -0.14
    isp
    -0.14
     Contents
    -0.14
    querque
    -0.13
    POSITIVE LOGITS
    /all
    0.22
    place
    0.20
    /e
    0.20
     kind
    0.19
    combination
    0.18
    where
    0.18
     combination
    0.17
    THING
    0.16
    hoo
    0.16
    uzzer
    0.16
    Act Density 0.052%

    No Known Activations