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

    Neuronpedia

    INDEX
    Explanations

    special characters likely specific to the model, potentially used as markers or embeddings for certain concepts or entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical values or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mub
    -0.81
     Robot
    -0.80
     crocod
    -0.77
     Haku
    -0.76
     Ag
    -0.76
     Sob
    -0.72
     Tier
    -0.72
     Solomon
    -0.71
     Liter
    -0.70
     Ide
    -0.70
    POSITIVE LOGITS
    Loading
    1.27
    together
    1.27
    ó
    1.22
    matter
    1.20
    Page
    1.18
    Commission
    1.18
    older
    1.18
    administ
    1.17
    that
    1.17
    said
    1.17
    Act Density 0.196%

    No Known Activations