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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating academic achievements or qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    </tfoot>
    -0.52
     everything
    -0.51
    EROS
    -0.51
    ружи
    -0.50
    sili
    -0.49
    INH
    -0.48
    cnpj
    -0.48
    ayas
    -0.48
    WISH
    -0.48
    similiano
    -0.48
    POSITIVE LOGITS
    LEncoder
    0.83
    AsUp
    0.77
    HideFlags
    0.71
     الحره
    0.69
    same
    0.67
     насељу
    0.67
    ItemBackground
    0.64
    ThemeOverlay
    0.64
    Same
    0.63
    Again
    0.62
    Act Density 0.376%

    No Known Activations