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

    Neuronpedia

    INDEX
    Explanations

    The main thing this neuron does is find words related to overriding or overruling something

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of "overriding" or "overridden," often in legal or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.78
    istics
    -0.72
    Sham
    -0.70
    ¯¯¯¯
    -0.70
     Drum
    -0.68
    Gamer
    -0.67
    Torrent
    -0.66
    dar
    -0.65
    pring
    -0.65
    fare
    -0.64
    POSITIVE LOGITS
     overr
    1.01
    idden
    0.99
    uled
    0.89
    xual
    0.87
     override
    0.83
    uling
    0.74
    ides
    0.73
     overriding
    0.71
    ulation
    0.70
    ulator
    0.67
    Act Density 0.023%

    No Known Activations