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

    Neuronpedia

    INDEX
    Explanations

    names of political figures

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, specifically commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nih
    -0.71
    grain
    -0.66
    ood
    -0.65
    continental
    -0.65
    amorph
    -0.64
    interstitial
    -0.63
    eries
    -0.61
    Availability
    -0.61
    idepress
    -0.60
     nightmares
    -0.60
    POSITIVE LOGITS
     meanwhile
    1.21
     however
    0.93
     unsurprisingly
    0.85
     huh
    0.84
     pictured
    0.84
     Bullets
    0.80
     citing
    0.78
     meantime
    0.73
     moreover
    0.72
     Sr
    0.70
    Act Density 0.344%

    No Known Activations