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

    Neuronpedia

    INDEX
    Explanations

    words indicating positive outcomes or advantages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Perkins
    -0.15
     khá»ıi
    -0.15
    adoras
    -0.14
    isas
    -0.14
    asaki
    -0.14
    ewise
    -0.14
    oppel
    -0.14
    zin
    -0.14
    esor
    -0.14
    styled
    -0.14
    POSITIVE LOGITS
    rees
    0.16
    748
    0.16
     re
    0.15
    olen
    0.14
    olland
    0.14
     Campos
    0.14
    weise
    0.14
    strain
    0.14
     dlg
    0.14
    chema
    0.13
    Act Density 0.012%

    No Known Activations