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

    Neuronpedia

    INDEX
    Explanations

    phrases related to exploration and discovery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wie
    -0.15
    ulkan
    -0.15
    .Sdk
    -0.15
    retty
    -0.14
    cassert
    -0.14
    statt
    -0.14
    readcr
    -0.14
    िब
    -0.14
    ecz
    -0.14
    .getOwnProperty
    -0.14
    POSITIVE LOGITS
     possibilities
    0.18
     depth
    0.18
     depths
    0.17
     deeper
    0.17
     options
    0.17
    depth
    0.17
     explore
    0.16
     deepest
    0.16
     Depth
    0.16
     rabbit
    0.15
    Act Density 0.075%

    No Known Activations