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, particularly in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thus
    -0.70
    corn
    -0.68
     Ala
    -0.68
     Camel
    -0.67
    gran
    -0.67
     Gall
    -0.65
    ramer
    -0.64
    agne
    -0.63
    avis
    -0.63
    ghazi
    -0.63
    POSITIVE LOGITS
     sensitivity
    1.30
    ivities
    1.14
    ensitivity
    0.99
     sensit
    0.97
     sensitive
    0.95
    irtual
    0.89
    itivity
    0.87
    ensitive
    0.85
    xual
    0.85
    itized
    0.84
    Act Density 0.009%

    No Known Activations