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

    Neuronpedia

    INDEX
    Explanations

    names of plants and specific physical objects

    oai_token-act-pair · gpt-3.5-turbo

    references to specific objects or entities, especially in scientific or technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.98
     Bows
    -0.88
     Deaths
    -0.86
    ounces
    -0.84
    IPS
    -0.84
     Sparks
    -0.82
     Winds
    -0.81
    Salt
    -0.81
     Owens
    -0.81
     Indigo
    -0.79
    POSITIVE LOGITS
     item
    1.15
     device
    1.14
     vehicle
    1.10
     site
    1.09
     panel
    1.09
     party
    1.07
     plane
    1.06
     board
    1.05
     customer
    1.04
     unit
    1.04
    Act Density 0.326%

    No Known Activations