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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a role or function

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hazel
    -0.17
    antro
    -0.17
    urma
    -0.15
    ildo
    -0.15
    ãĤĩ
    -0.14
    VERRIDE
    -0.14
    icorn
    -0.14
     Mez
    -0.14
    kf
    -0.14
    prit
    -0.14
    POSITIVE LOGITS
     parte
    0.14
     Hardcore
    0.14
    ato
    0.14
     fort
    0.14
    ogh
    0.14
     Cunning
    0.14
    pects
    0.13
     Zucker
    0.13
     abs
    0.13
     lev
    0.13
    Act Density 0.264%

    No Known Activations