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

    Neuronpedia

    INDEX
    Explanations

    words related to sensitivity

    oai_token-act-pair · gpt-3.5-turbo

    references to sensitivity across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Camel
    -0.76
    agher
    -0.75
    corn
    -0.72
     Eternity
    -0.72
    ghazi
    -0.72
     Rao
    -0.70
    raine
    -0.69
    agne
    -0.66
     Ala
    -0.66
     Saga
    -0.66
    POSITIVE LOGITS
    ivities
    1.17
     sensitivity
    1.13
     sensit
    0.94
    ensitivity
    0.92
     sensitive
    0.88
     tolerant
    0.86
    itivity
    0.85
    itized
    0.83
    ensitive
    0.81
    uous
    0.80
    Act Density 0.015%

    No Known Activations