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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating intention or purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.98
    LookAnd
    -0.80
     propOrder
    -0.78
    Geplaatst
    -0.78
     مشين
    -0.75
    IntoConstraints
    -0.72
     indisponible
    -0.72
    GEBURTSDATUM
    -0.71
    WriteTagHelper
    -0.70
    SqlSession
    -0.69
    POSITIVE LOGITS
     seems
    0.70
     seem
    0.65
     semblent
    0.54
    seems
    0.53
     sembrano
    0.53
     seemed
    0.52
    似乎
    0.51
     semble
    0.49
     tampaknya
    0.48
    thusi
    0.48
    Act Density 0.147%

    No Known Activations