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

    Neuronpedia

    INDEX
    Explanations

    comparisons using "like a..." phrases

    oai_token-act-pair · gpt-3.5-turbo

    constructions that begin with "like a," indicating comparisons or similes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     furthermore
    -0.79
     additionally
    -0.77
    Events
    -0.75
    nces
    -0.72
     ALSO
    -0.72
    notes
    -0.71
    iments
    -0.71
    msg
    -0.69
    videos
    -0.68
    autions
    -0.67
    POSITIVE LOGITS
     typical
    1.01
     bunch
    0.92
     normal
    0.91
     sponge
    0.88
     traditional
    0.86
     snail
    0.85
     regular
    0.83
     miniature
    0.82
     lot
    0.81
     predator
    0.78
    Act Density 0.194%

    No Known Activations