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

    Neuronpedia

    INDEX
    Explanations

    references to expertise, mastery, or high-quality execution in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    te
    -0.17
    yaw
    -0.17
    noc
    -0.17
    ema
    -0.16
    nel
    -0.16
    nal
    -0.16
    til
    -0.15
    sla
    -0.15
     Pert
    -0.15
    ologist
    -0.15
    POSITIVE LOGITS
    mind
    0.36
    pieces
    0.32
    stroke
    0.27
    piece
    0.26
    ful
    0.25
    fully
    0.23
    class
    0.23
    /master
    0.22
    classes
    0.22
    (master
    0.20
    Act Density 0.022%

    No Known Activations