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

    Neuronpedia

    INDEX
    Explanations

    words related to parks and recreational activities

    oai_token-act-pair · gpt-3.5-turbo

    references to parks and related organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ded
    -0.72
    jad
    -0.69
    oldemort
    -0.68
    ients
    -0.65
    rates
    -0.62
     diagnosis
    -0.61
    atever
    -0.60
    verages
    -0.60
    uders
    -0.57
     calcul
    -0.57
    POSITIVE LOGITS
    conservancy
    1.01
    manship
    0.99
    afety
    0.97
    cape
    0.84
    crew
    0.84
    itect
    0.83
    mallow
    0.83
    park
    0.81
    erver
    0.80
    ynski
    0.79
    Act Density 0.029%

    No Known Activations