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

    Neuronpedia

    INDEX
    Explanations

    comparisons or enhancements between different elements

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating changes or improvements over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iol
    -0.68
    Limited
    -0.62
    ãĤĬ
    -0.62
    FG
    -0.60
    Premium
    -0.60
    IQ
    -0.60
     (%
    -0.59
    endale
    -0.58
     Isles
    -0.57
    wind
    -0.57
    POSITIVE LOGITS
     ours
    0.80
    gypt
    0.78
     Jas
    0.77
     typical
    0.76
     traditional
    0.75
     usual
    0.74
     predecessors
    0.74
     previous
    0.74
     counterparts
    0.73
     predecessor
    0.72
    Act Density 0.555%

    No Known Activations