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

    Neuronpedia

    INDEX
    Explanations

    instances of products or items being available in different colors or versions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the availability or arrival of products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingham
    -0.75
    orthodox
    -0.72
    fts
    -0.66
    ruff
    -0.65
    idav
    -0.65
    ivas
    -0.63
    iple
    -0.63
    ricular
    -0.63
    imon
    -0.63
    oris
    -0.63
    POSITIVE LOGITS
     undone
    0.96
     packaged
    0.90
     nowhere
    0.80
     forth
    0.76
     ashore
    0.75
     along
    0.73
     equipped
    0.73
     roaring
    0.72
     peril
    0.72
     closest
    0.70
    Act Density 0.084%

    No Known Activations