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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to changes or transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.79
     المعيارى
    -0.78
    DockStyle
    -0.76
    migrationBuilder
    -0.74
    Rhestr
    -0.71
    ModelAdmin
    -0.69
    énario
    -0.68
    DeleteBehavior
    -0.67
    BufferException
    -0.63
    RegistryLite
    -0.63
    POSITIVE LOGITS
     Miele
    0.49
     dries
    0.49
     Occur
    0.47
     occur
    0.47
     disparu
    0.47
     out
    0.46
     up
    0.45
     vécu
    0.45
    YMMV
    0.43
     näky
    0.42
    Act Density 0.586%

    No Known Activations