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

    Neuronpedia

    INDEX
    Explanations

    punctuation and certain contractions or abbreviations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igger
    -0.16
    erli
    -0.15
    hani
    -0.15
    .opens
    -0.14
    antar
    -0.14
    .hw
    -0.14
    lesi
    -0.14
     Redistributions
    -0.14
    egra
    -0.14
     dog
    -0.14
    POSITIVE LOGITS
    ÂĢÂĻ
    0.17
    ruk
    0.15
    avia
    0.15
    iž
    0.14
    owi
    0.14
    inges
    0.14
    ako
    0.14
    éĻ½
    0.14
    TZ
    0.14
    .tools
    0.14
    Act Density 0.100%

    No Known Activations