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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hol
    -0.15
     negot
    -0.14
    ure
    -0.14
    bler
    -0.14
    Ø°
    -0.13
    osc
    -0.13
    ält
    -0.13
     hel
    -0.13
     fractions
    -0.13
    man
    -0.13
    POSITIVE LOGITS
    oir
    0.16
    ucch
    0.15
    ocity
    0.15
    ettle
    0.15
    UPI
    0.14
    łĢ
    0.14
    alach
    0.14
    á¿Ĩ
    0.14
    emit
    0.14
     Lage
    0.14
    Act Density 0.061%

    No Known Activations