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

    Neuronpedia

    INDEX
    Explanations

    general statements or opinions expressed about various subjects

    oai_token-act-pair · gpt-3.5-turbo

    phrases referring to entities, organizations, or individuals that are actively doing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sources
    -0.74
     Cars
    -0.68
     Savings
    -0.66
     VIDEOS
    -0.65
    Box
    -0.64
     Ahead
    -0.64
    ãĥŁ
    -0.63
    strom
    -0.62
     Seller
    -0.62
     Dude
    -0.59
    POSITIVE LOGITS
     specialize
    0.79
     satisfies
    0.72
    ereo
    0.71
     distinguishes
    0.71
     compares
    0.70
     fits
    0.70
     qualifies
    0.69
     deserve
    0.69
    makes
    0.68
     ought
    0.68
    Act Density 0.178%

    No Known Activations