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

    Neuronpedia

    INDEX
    Explanations

    terms related to measurements and analysis in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    丸
    -0.16
    (es
    -0.15
    ml
    -0.15
     (
    -0.15
    ettel
    -0.15
    itura
    -0.15
    atter
    -0.14
    ene
    -0.14
    uster
    -0.14
    oningen
    -0.14
    POSITIVE LOGITS
    atre
    0.16
    -valu
    0.15
    oret
    0.15
    WebResponse
    0.14
    EDGE
    0.14
    âĨĵ
    0.14
    .tf
    0.14
    riv
    0.14
    reff
    0.14
    iless
    0.14
    Act Density 0.238%

    No Known Activations