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

    Neuronpedia

    INDEX
    Explanations

    terms related to research and commercial-grade technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (es
    -0.16
    emies
    -0.16
    opsis
    -0.15
    emean
    -0.15
    lessness
    -0.14
    ipt
    -0.14
    ieves
    -0.14
     Wealth
    -0.14
    yll
    -0.14
    VD
    -0.14
    POSITIVE LOGITS
    -grade
    0.57
     grade
    0.55
    grade
    0.47
     Grade
    0.40
    Grade
    0.39
    级
    0.32
    -sized
    0.32
    -scale
    0.31
    _grade
    0.31
    .grade
    0.30
    Act Density 0.287%

    No Known Activations