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

    Neuronpedia

    INDEX
    Explanations

    references to roles, positions, and service in professional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    HIR
    -0.18
    ouver
    -0.17
    issor
    -0.15
    achs
    -0.15
    ola
    -0.15
    era
    -0.15
     virgin
    -0.15
    ستاÙĨ
    -0.14
    lica
    -0.14
    ulin
    -0.14
    POSITIVE LOGITS
    illance
    0.20
    .scalablytyped
    0.18
    arrants
    0.16
    tle
    0.15
    æŀľ
    0.15
    éĹ
    0.15
    ords
    0.14
    ardash
    0.14
    ãĥ³ãĥĩãĤ£
    0.13
    ooter
    0.13
    Act Density 0.023%

    No Known Activations