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

    Neuronpedia

    INDEX
    Explanations

    words or terms that end with the suffix "ine."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ctor
    -0.18
    atile
    -0.15
    otland
    -0.15
    frica
    -0.15
    ner
    -0.15
    nt
    -0.14
    tron
    -0.14
    istrovstvÃŃ
    -0.14
    wy
    -0.14
    misc
    -0.14
    POSITIVE LOGITS
    jad
    0.23
    utral
    0.20
    ighbour
    0.20
    ering
    0.20
    ymoon
    0.19
    uve
    0.19
    alogy
    0.18
    ighbours
    0.18
    ighb
    0.18
    ked
    0.18
    Act Density 0.066%

    No Known Activations