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

    Neuronpedia

    INDEX
    Explanations

    terms related to knowledge or expertise in specific areas

    oai_token-act-pair · gpt-3.5-turbo

    references to knowledge or understanding in various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idal
    -0.78
    earchers
    -0.72
    orthy
    -0.70
    eca
    -0.67
    ratulations
    -0.65
    roid
    -0.65
    appointed
    -0.63
    assador
    -0.63
     happiest
    -0.63
    Alert
    -0.62
    POSITIVE LOGITS
     languages
    1.07
     english
    1.03
     mathematics
    1.00
     geography
    1.00
     maths
    0.99
     basics
    0.97
     biology
    0.96
     ropes
    0.95
     anatomy
    0.95
     physics
    0.93
    Act Density 0.338%

    No Known Activations