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

    Neuronpedia

    INDEX
    Explanations

    terms related to utility and helpfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edb
    -0.17
    ed
    -0.17
    olley
    -0.15
    CHED
    -0.14
    aning
    -0.14
    ilet
    -0.14
    rav
    -0.14
    gor
    -0.14
    isko
    -0.14
    iaz
    -0.14
    POSITIVE LOGITS
    /help
    0.21
     ÃŃch
    0.19
    /use
    0.18
    lest
    0.18
    fully
    0.18
    /product
    0.17
    mente
    0.16
     tool
    0.16
    ness
    0.15
    iences
    0.15
    Act Density 0.044%

    No Known Activations