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

    Neuronpedia

    INDEX
    Explanations

    terms related to morality and ethical judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iferay
    -0.18
    arranty
    -0.18
    ãĥ³ãĥij
    -0.15
    ostel
    -0.15
     Guth
    -0.15
    lehem
    -0.14
    rung
    -0.14
    ilim
    -0.14
    ÙĬÙĩ
    -0.14
    .UnitTesting
    -0.14
    POSITIVE LOGITS
     ä¸ī
    0.28
     trio
    0.28
     three
    0.27
     Three
    0.27
    ä¸ī
    0.27
    3
    0.26
     THREE
    0.25
     threesome
    0.25
    -three
    0.24
     ÃľÃ§
    0.24
    Act Density 0.485%

    No Known Activations