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

    Neuronpedia

    INDEX
    Explanations

    terms related to scientific concepts and research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ted
    -0.18
    steller
    -0.16
    ting
    -0.15
    ingham
    -0.15
    gether
    -0.15
    rescia
    -0.15
    ulses
    -0.15
    rees
    -0.15
    roit
    -0.15
    rieved
    -0.14
    POSITIVE LOGITS
    /engine
    0.20
    /stat
    0.19
    /math
    0.18
    owl
    0.17
    /art
    0.15
    -fiction
    0.15
    riminator
    0.14
    OWL
    0.14
    yonel
    0.13
    ifice
    0.13
    Act Density 0.048%

    No Known Activations