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

    Neuronpedia

    INDEX
    Explanations

    phrasing that emphasizes instance of attribution or authorship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esso
    -0.20
    icts
    -0.14
    ardo
    -0.14
    ики
    -0.13
    quares
    -0.13
     Recommendation
    -0.13
    lector
    -0.13
    oric
    -0.13
    ince
    -0.13
    sembler
    -0.13
    POSITIVE LOGITS
    uiltin
    0.15
     меÑĢе
    0.15
    rog
    0.15
    alous
    0.14
     masc
    0.14
    alara
    0.14
    oS
    0.14
    ezier
    0.14
    alic
    0.14
    oxid
    0.14
    Act Density 0.005%

    No Known Activations