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

    Neuronpedia

    INDEX
    Explanations

    values associated with experimental or statistical data

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.85
    findpost
    -0.77
     otomatig
    -0.76
     <=",
    -0.76
     gynhyrchwyd
    -0.74
     ProtoMessage
    -0.71
    ValueStyle
    -0.71
    MigrationBuilder
    -0.69
    Хьажоргаш
    -0.68
     صوتيه
    -0.68
    POSITIVE LOGITS
     purpoſe
    0.56
     Recogn
    0.51
     pleaſure
    0.51
     Nau
    0.50
    gros
    0.50
     Piv
    0.49
     Sols
    0.48
    olon
    0.47
     reaſon
    0.47
    Instru
    0.47
    Act Density 0.003%

    No Known Activations