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

    Neuronpedia

    INDEX
    Explanations

    phrases related to proposals, efforts, and commitments towards development and sustainability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ever
    -0.15
    央
    -0.15
     fulfil
    -0.14
     ambition
    -0.14
     devast
    -0.14
    _require
    -0.14
    iltr
    -0.13
    inish
    -0.13
    gle
    -0.13
    aque
    -0.13
    POSITIVE LOGITS
     sensit
    0.23
     sens
    0.19
     upscale
    0.19
     mainstream
    0.18
     popular
    0.18
    popular
    0.17
     capac
    0.17
     Sens
    0.17
    ief
    0.15
    hra
    0.15
    Act Density 0.191%

    No Known Activations