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

    Neuronpedia

    INDEX
    Explanations

    specific numeric values or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     scoped
    -0.07
     minor
    -0.07
    ertz
    -0.06
    ANDOM
    -0.06
    olley
    -0.06
    atar
    -0.06
     kem
    -0.06
    etik
    -0.06
    ema
    -0.05
    anut
    -0.05
    POSITIVE LOGITS
    -Cs
    0.07
     件
    0.07
    axe
    0.07
     prefect
    0.07
     addCriterion
    0.07
    ãĤıãģĽ
    0.07
    Monkey
    0.07
    -valu
    0.07
     Pole
    0.07
    ãĤ¿ãĥ³
    0.06
    Act Density 0.000%

    No Known Activations