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

    Neuronpedia

    INDEX
    Explanations

    similes that involve shaking or physical movement

    oai_token-act-pair · gpt-3.5-turbo

    similes that use the structure "like a."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alties
    -0.79
     furthermore
    -0.78
    Events
    -0.78
    bars
    -0.78
    abilities
    -0.76
    videos
    -0.75
     Adin
    -0.75
    advertisement
    -0.74
    Whether
    -0.73
    encies
    -0.73
    POSITIVE LOGITS
     bunch
    1.04
     typical
    0.92
     sponge
    0.90
     proverbial
    0.87
     lot
    0.87
     precursor
    0.87
     mixture
    0.85
     maniac
    0.83
     gateway
    0.83
     normal
    0.83
    Act Density 0.117%

    No Known Activations