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

    Neuronpedia

    INDEX
    Explanations

    references to food and grocery-related activities and items

    oai_token-act-pair · gpt-3.5-turbo

    references to shopping or retail environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roup
    -0.61
    afort
    -0.59
    Reloaded
    -0.58
    ranging
    -0.58
    Reviewer
    -0.58
    cul
    -0.58
    prim
    -0.57
     Species
    -0.56
    External
    -0.56
     Vessel
    -0.56
    POSITIVE LOGITS
     anymore
    1.01
     or
    0.90
     tomorrow
    0.83
    washer
    0.79
     screaming
    0.77
     clutching
    0.77
     waving
    0.75
    arettes
    0.74
     goodbye
    0.74
     sweating
    0.72
    Act Density 0.812%

    No Known Activations