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

    Neuronpedia

    INDEX
    Explanations

    references to rabbits

    oai_token-act-pair · gpt-3.5-turbo

    references to rabbits and related imagery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    omething
    -0.90
    igmat
    -0.79
    ician
    -0.76
    inia
    -0.76
    inen
    -0.74
    rylic
    -0.74
    ructure
    -0.73
    orie
    -0.70
    itutional
    -0.69
    eatures
    -0.69
    POSITIVE LOGITS
    MQ
    1.07
     rabbit
    0.94
     Rabbit
    0.94
     Hole
    0.91
    meat
    0.88
     rabbits
    0.83
    fish
    0.80
     Nest
    0.79
     Hunt
    0.78
    gey
    0.75
    Act Density 0.013%

    No Known Activations