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

    Neuronpedia

    INDEX
    Explanations

    instances of objects being moved or placed into various locations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to descent or being submerged

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chool
    -0.77
    sense
    -0.76
    essential
    -0.75
    illac
    -0.73
    encer
    -0.72
    staff
    -0.71
    paren
    -0.70
    erning
    -0.69
    cription
    -0.68
    employed
    -0.68
    POSITIVE LOGITS
     landfill
    1.09
     sea
    1.08
     lava
    1.00
     unpop
    0.98
     dumps
    0.96
     lake
    0.96
     pits
    0.95
     heap
    0.94
     abyss
    0.94
     ditch
    0.94
    Act Density 0.221%

    No Known Activations