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

    Neuronpedia

    INDEX
    Explanations

    dates and time periods

    oai_token-act-pair · gpt-3.5-turbo

    dates and time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     corrid
    -0.71
     listened
    -0.67
     teasp
    -0.65
     rubbed
    -0.65
     waited
    -0.65
     unden
    -0.62
     tur
    -0.62
     reverence
    -0.61
     sung
    -0.60
     investigated
    -0.60
    POSITIVE LOGITS
    ghan
    0.78
    vier
    0.70
    yne
    0.69
     onwards
    0.67
    0.65
    acers
    0.65
    andy
    0.65
    zie
    0.65
    iles
    0.64
     onward
    0.63
    Act Density 0.125%

    No Known Activations