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

    Neuronpedia

    INDEX
    Explanations

    terms related to authority and hierarchy in religious contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.85
     itſelf
    -0.85
    itarianism
    -0.77
     ſche
    -0.76
    ergies
    -0.75
    MigrationBuilder
    -0.75
     purpoſe
    -0.75
    OGND
    -0.75
     ſtate
    -0.74
     equator
    -0.73
    POSITIVE LOGITS
     their
    0.59
    ,
    0.47
    :
    0.46
     —
    0.45
     leurs
    0.45
     are
    0.43
     over
    0.43
     --
    0.42
    <bos>
    0.42
     Their
    0.42
    Act Density 0.102%

    No Known Activations