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

    Neuronpedia

    INDEX
    Explanations

    references to performance metrics or criteria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    resse
    -0.17
    icom
    -0.16
     affair
    -0.16
    -0.16
    -headed
    -0.15
    red
    -0.15
    ling
    -0.15
    -quarters
    -0.15
    irement
    -0.15
    ноÑģÑıÑĤ
    -0.15
    POSITIVE LOGITS
    razier
    0.17
    ances
    0.17
    eÄį
    0.16
    eum
    0.16
    adox
    0.16
     trou
    0.15
    ividad
    0.14
    ative
    0.14
     Haj
    0.14
    eur
    0.14
    Act Density 0.044%

    No Known Activations