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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to statistics and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lier
    -0.17
    IMP
    -0.17
     rocket
    -0.16
    uns
    -0.16
    dbg
    -0.15
    ua
    -0.15
     beyond
    -0.14
    ikt
    -0.14
    orsch
    -0.14
    ãĥijãĥ³
    -0.14
    POSITIVE LOGITS
    ÏĦικ
    0.16
    rax
    0.16
    oko
    0.15
    ncoder
    0.15
    hots
    0.14
    Enumeration
    0.14
    UBLE
    0.14
    amilia
    0.14
     BaseType
    0.14
     Hein
    0.14
    Act Density 0.336%

    No Known Activations