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

    Neuronpedia

    INDEX
    Explanations

    actions related to legal or technical modifications or interventions

    oai_token-act-pair · gpt-3.5-turbo

    past participles related to legal or medical actions and status changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asio
    -0.77
    idth
    -0.73
    uggest
    -0.72
    omething
    -0.69
     Flavoring
    -0.66
    clerosis
    -0.65
    rg
    -0.65
    orr
    -0.64
    RESULTS
    -0.63
    column
    -0.62
    POSITIVE LOGITS
     intact
    0.74
     nationally
    0.71
     by
    0.69
     loose
    0.69
     BY
    0.67
     centrally
    0.67
    uled
    0.66
     abl
    0.65
     alive
    0.64
     across
    0.64
    Act Density 0.205%

    No Known Activations