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

    Neuronpedia

    INDEX
    Explanations

    references to metal and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eniable
    -0.19
    eldon
    -0.17
    es
    -0.16
    ester
    -0.16
    ety
    -0.16
    eyim
    -0.15
    ystone
    -0.15
    erte
    -0.15
    ÙĨ
    -0.14
    automation
    -0.14
    POSITIVE LOGITS
    licity
    0.36
    lica
    0.32
    lic
    0.28
    anguage
    0.27
    urgical
    0.25
    working
    0.23
    workers
    0.23
    mith
    0.23
    urgy
    0.22
    lico
    0.22
    Act Density 0.015%

    No Known Activations