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

    Neuronpedia

    INDEX
    Explanations

    financial terms and activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation or the use of commas in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ernels
    -0.80
    ities
    -0.79
    lees
    -0.72
     repositories
    -0.66
     detectors
    -0.66
     idols
    -0.64
    riers
    -0.64
    izens
    -0.64
     disciplines
    -0.63
     departments
    -0.63
    POSITIVE LOGITS
     consisting
    0.93
     wherein
    0.85
    albeit
    0.83
     albeit
    0.82
     preferably
    0.80
     resembling
    0.79
     whereby
    0.78
    shapeshifter
    0.77
     comprising
    0.75
    circle
    0.72
    Act Density 0.846%

    No Known Activations