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

    Neuronpedia

    INDEX
    Explanations

    expressions of visibility or clarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Darling
    -0.17
    enburg
    -0.15
    abilité
    -0.14
    Enlarge
    -0.14
    kel
    -0.14
    Exact
    -0.14
    ámara
    -0.14
    wolf
    -0.13
    istro
    -0.13
    pte
    -0.13
    POSITIVE LOGITS
     perce
    0.17
    rypted
    0.15
     Dud
    0.15
     Rog
    0.15
    addOn
    0.15
    oded
    0.14
    orer
    0.14
    alom
    0.14
    /lang
    0.14
     ########.
    0.14
    Act Density 0.144%

    No Known Activations