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

    Neuronpedia

    INDEX
    Explanations

    references to formal titles, roles, or official correspondence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yn
    -0.15
     mature
    -0.14
    ÑĢд
    -0.14
    jours
    -0.14
     Pag
    -0.14
     Sle
    -0.14
    }elseif
    -0.14
    ÙĪرÛĮ
    -0.13
     steer
    -0.13
     maturity
    -0.13
    POSITIVE LOGITS
    à¸IJ
    0.15
     Hoy
    0.15
    urette
    0.15
    prm
    0.15
    rix
    0.14
    .tex
    0.14
    ió
    0.14
    meric
    0.14
    iless
    0.14
     Huss
    0.14
    Act Density 0.024%

    No Known Activations