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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and equations involving variables and numerical relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     primary
    -0.46
    Primary
    -0.46
     Primary
    -0.44
    primary
    -0.41
    рави
    -0.40
     مؤرشف
    -0.40
     chắn
    -0.39
    вање
    -0.39
     “
    -0.38
     }^{*
    -0.38
    POSITIVE LOGITS
     estekak
    0.93
    UnusedPrivate
    0.90
     للاسماء
    0.84
    ThroughAttribute
    0.82
    HomeAsUpEnabled
    0.81
    PreferredItem
    0.77
    tvguidetime
    0.74
     noDo
    0.74
     beginnetje
    0.72
    Personensuche
    0.70
    Act Density 1.610%

    No Known Activations