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

    Neuronpedia

    INDEX
    Explanations

    relationships between actions and their outcomes or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.44
    Lycka
    -0.42
     Económica
    -0.42
     Verfassung
    -0.41
     Relaciones
    -0.41
    IUrlHelper
    -0.41
     rayas
    -0.41
    tanleria
    -0.40
    %)$
    -0.40
     informée
    -0.40
    POSITIVE LOGITS
    tock
    0.57
    tocks
    0.50
    ritic
    0.50
    peted
    0.50
    timate
    0.47
     SAF
    0.47
    europa
    0.47
    bern
    0.47
    idor
    0.47
     Deb
    0.47
    Act Density 0.036%

    No Known Activations