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

    Neuronpedia

    INDEX
    Explanations

    statements and discussions emphasizing objective facts and their verification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eb
    -0.15
    innen
    -0.15
    ded
    -0.15
    iggs
    -0.15
    dy
    -0.14
     fine
    -0.14
    itz
    -0.14
    ocker
    -0.14
    tle
    -0.14
    .idx
    -0.14
    POSITIVE LOGITS
    facts
    0.23
     facts
    0.20
    itious
    0.18
    intl
    0.18
    urtle
    0.17
    Fact
    0.16
     Facts
    0.16
    aland
    0.16
    oring
    0.16
    gravity
    0.16
    Act Density 0.026%

    No Known Activations