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

    Neuronpedia

    INDEX
    Explanations

    references to fairness or equitable practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     other
    -1.67
     maternal
    -1.46
     its
    -1.45
     latest
    -1.42
     elevated
    -1.40
    esters
    -1.38
    plasia
    -1.38
     elderly
    -1.38
     beautiful
    -1.37
     previous
    -1.37
    POSITIVE LOGITS
    fax
    2.01
    banks
    1.94
    uet
    1.85
    opan
    1.82
    manship
    1.71
    cloth
    1.71
    grounds
    1.70
    gate
    1.70
    leigh
    1.70
    piece
    1.64
    Act Density 0.018%

    No Known Activations