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

    Neuronpedia

    INDEX
    Explanations

    terms related to disciplinary actions and disclosures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terior
    -0.17
    est
    -0.16
    ters
    -0.16
    .jupiter
    -0.16
    icks
    -0.15
    ched
    -0.15
    emale
    -0.15
    chod
    -0.15
    ioned
    -0.15
    onte
    -0.15
    POSITIVE LOGITS
    yard
    0.19
    urre
    0.18
    ursive
    0.18
    .gg
    0.17
    ãĥ©ãĥ³ãĥī
    0.17
    iplinary
    0.17
    озд
    0.16
    folio
    0.16
    LAT
    0.16
    .scalablytyped
    0.16
    Act Density 0.037%

    No Known Activations