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

    Neuronpedia

    INDEX
    Explanations

    phrases related to societal issues or structures

    oai_token-act-pair · gpt-3.5-turbo

    the definite article "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     today
    -0.66
     tonight
    -0.61
     whence
    -0.59
     yesterday
    -0.58
    elsen
    -0.57
     tomorrow
    -0.56
     the
    -0.56
     Germany
    -0.55
    verage
    -0.55
     thanked
    -0.55
    POSITIVE LOGITS
    ocratic
    1.11
    ses
    1.08
     occasional
    1.07
    urgy
    1.05
    ocracy
    0.95
    atre
    0.95
     usual
    0.94
     slightest
    0.92
    ologically
    0.89
     basics
    0.88
    Act Density 0.347%

    No Known Activations