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

    Neuronpedia

    INDEX
    Explanations

    words related to technology and infrastructure

    oai_token-act-pair · gpt-3.5-turbo

    plural nouns and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥª
    -0.74
    é¾į
    -0.71
    ãĤ¦ãĤ¹
    -0.69
    shapeshifter
    -0.65
    èª
    -0.64
    Bey
    -0.64
    î
    -0.62
    ¾
    -0.60
    è»
    -0.60
    duc
    -0.60
    POSITIVE LOGITS
    wana
    0.99
    ource
    0.98
    afety
    0.97
    cript
    0.96
    hip
    0.95
    hift
    0.95
    hips
    0.94
    kaya
    0.92
    ilver
    0.89
    lash
    0.87
    Act Density 0.178%

    No Known Activations