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

    Neuronpedia

    INDEX
    Explanations

    the word "the" and other high-frequency terms indicating common nouns or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Stamp
    -0.16
    asad
    -0.16
    hoff
    -0.15
    ãģĭãģĹ
    -0.15
    .CopyTo
    -0.15
    ersh
    -0.14
    krát
    -0.14
    aña
    -0.14
     stamps
    -0.14
    hof
    -0.14
    POSITIVE LOGITS
    -way
    0.15
    urret
    0.15
     straw
    0.15
    ollow
    0.15
    é¼
    0.14
    dık
    0.14
     makeStyles
    0.14
    field
    0.14
    OrNil
    0.14
    ippet
    0.14
    Act Density 0.003%

    No Known Activations