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

    Neuronpedia

    INDEX
    Explanations

    references to the health and well-being of whales

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nest
    -0.19
     rabbit
    -0.18
     rabbits
    -0.18
     lattice
    -0.17
    atti
    -0.17
    udit
    -0.15
     spiders
    -0.15
     lizard
    -0.15
     Nest
    -0.15
     Tro
    -0.14
    POSITIVE LOGITS
     cet
    0.36
     whales
    0.32
     bott
    0.31
     whale
    0.30
     pod
    0.29
     pods
    0.29
     Killer
    0.28
     killer
    0.28
     sperm
    0.28
     Pods
    0.27
    Act Density 0.140%

    No Known Activations