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

    Neuronpedia

    INDEX
    Explanations

    assertions about truth and validity in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SharedDtor
    -0.67
    DockStyle
    -0.67
    >>>>>>>
    -0.63
    -0.63
    ftagPool
    -0.62
    InjectAttribute
    -0.61
    љи
    -0.54
    <bos>
    -0.53
    MigrationBuilder
    -0.52
     geslacht
    -0.52
    POSITIVE LOGITS
     true
    2.81
    true
    2.46
     True
    2.20
    True
    2.19
     TRUE
    2.09
    TRUE
    1.91
     truth
    1.78
     truer
    1.66
     vrai
    1.56
     truest
    1.49
    Act Density 0.409%

    No Known Activations