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

    Neuronpedia

    INDEX
    Explanations

    references to batches or groups of items or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to multiple items or groups processed at once

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ruption
    -0.73
     Commissioners
    -0.70
    PLIED
    -0.67
    plex
    -0.66
    gling
    -0.65
     Cathedral
    -0.64
     Episcopal
    -0.63
    pose
    -0.63
    ophers
    -0.62
    relations
    -0.61
    POSITIVE LOGITS
     batches
    0.97
    mates
    0.97
     batch
    0.92
    mate
    0.74
    hari
    0.71
    TPS
    0.69
    meal
    0.69
    uling
    0.68
    olean
    0.67
    etooth
    0.66
    Act Density 0.020%

    No Known Activations