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

    Neuronpedia

    INDEX
    Explanations

    words related to economic conditions and changes

    oai_token-act-pair · gpt-3.5-turbo

    verb forms related to states of being or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    =-=-=-=-
    -0.76
    rarily
    -0.71
    ppings
    -0.69
    cific
    -0.69
    =-=-
    -0.67
     Lawn
    -0.66
     Quantity
    -0.63
    swer
    -0.63
     Moines
    -0.63
     Yates
    -0.62
    POSITIVE LOGITS
     becoming
    1.43
     poised
    1.32
     turning
    1.30
     accelerating
    1.29
     spreading
    1.27
     slowing
    1.27
     gaining
    1.27
     disappearing
    1.25
     changing
    1.23
     morp
    1.23
    Act Density 0.421%

    No Known Activations