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

    Neuronpedia

    INDEX
    Explanations

    references to the size or rank of entities in various categories

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rankings and measurements of sizes or capacities across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModLoader
    -0.61
     brilliance
    -0.61
     Panzer
    -0.61
     Jenkins
    -0.61
    tnc
    -0.59
     greatness
    -0.56
     prototypes
    -0.56
     madness
    -0.56
     likeness
    -0.55
     Roses
    -0.55
    POSITIVE LOGITS
    behind
    0.96
     globally
    0.93
     surveyed
    0.87
     respectively
    0.85
     worldwide
    0.84
    ever
    0.81
     behind
    0.79
    quartered
    0.79
     EVER
    0.79
     according
    0.77
    Act Density 0.235%

    No Known Activations