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

    Neuronpedia

    INDEX
    Explanations

    technical specifications related to electronic devices

    oai_token-act-pair · gpt-3.5-turbo

    references to specific model numbers or product versions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     teasp
    -0.64
    én
    -0.64
     gorge
    -0.63
    vertisement
    -0.62
    arov
    -0.62
    otrop
    -0.61
    undred
    -0.61
     Orders
    -0.60
     starved
    -0.60
     whisk
    -0.59
    POSITIVE LOGITS
    Edit
    0.85
    IDE
    0.81
    eus
    0.77
    Ds
    0.76
    VEN
    0.76
    PORT
    0.75
    TION
    0.73
    bis
    0.72
    xus
    0.72
    DS
    0.71
    Act Density 0.057%

    No Known Activations