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

    Neuronpedia

    INDEX
    Explanations

    references to scientific concepts and discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Science
    -0.23
     science
    -0.23
    science
    -0.23
    Science
    -0.22
    uma
    -0.18
    rescia
    -0.17
     scientifically
    -0.17
    ç§ijåѦ
    -0.17
    itre
    -0.17
     khoa
    -0.16
    POSITIVE LOGITS
    ally
    0.34
    /engine
    0.29
    ALLY
    0.22
    /math
    0.22
    -fiction
    0.20
    /art
    0.20
    ENCES
    0.18
    /stat
    0.17
    emet
    0.16
    american
    0.16
    Act Density 0.050%

    No Known Activations