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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating sequential or procedural actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Искәрмәләр
    -0.55
    #![
    -0.54
     Jau
    -0.53
    BuildContext
    -0.53
    nın
    -0.53
     Utica
    -0.52
     vest
    -0.52
    BORN
    -0.51
     future
    -0.51
     Vane
    -0.50
    POSITIVE LOGITS
     followed
    3.53
    followed
    3.13
     Followed
    3.07
    Followed
    2.75
     diikuti
    2.33
     suivie
    2.30
     seguido
    2.29
     seguida
    1.96
     suivi
    1.87
     accompanied
    1.72
    Act Density 0.149%

    No Known Activations