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

    Neuronpedia

    INDEX
    Explanations

    French phrases and components related to dramatic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     actual
    -0.15
    okens
    -0.15
    bourg
    -0.15
    adiens
    -0.15
    ìĤ¬ë¬´
    -0.14
    ÐĴÑĤ
    -0.14
     aras
    -0.14
    aÄŁa
    -0.13
    .openConnection
    -0.13
     Alejandro
    -0.13
    POSITIVE LOGITS
     ça
    0.18
    ATAL
    0.17
     Ingredient
    0.16
    iiii
    0.16
     Respir
    0.16
     chic
    0.16
     tranqu
    0.16
     dorm
    0.15
     pending
    0.15
     cach
    0.15
    Act Density 0.097%

    No Known Activations