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

    Neuronpedia

    INDEX
    Explanations

    mentions of cages, especially related to pets

    oai_token-act-pair · gpt-3.5-turbo

    references to cages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bundes
    -0.76
    ACTED
    -0.71
     Nare
    -0.68
    IELD
    -0.68
    ibel
    -0.63
    olitan
    -0.63
    velength
    -0.62
     lender
    -0.61
     Fargo
    -0.60
    igate
    -0.60
    POSITIVE LOGITS
     cage
    0.99
     cages
    0.97
    door
    0.95
    washer
    0.83
    pit
    0.81
    hold
    0.80
     Cage
    0.79
    mong
    0.76
    ModLoader
    0.72
    doors
    0.72
    Act Density 0.024%

    No Known Activations