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

    Neuronpedia

    INDEX
    Explanations

    words related to time duration or extended periods

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    iquette
    -0.67
    anic
    -0.65
    origin
    -0.61
    Nation
    -0.61
    DON
    -0.61
    met
    -0.60
    %]
    -0.60
     reconc
    -0.59
     helicop
    -0.58
    ocl
    -0.58
    POSITIVE LOGITS
     ago
    0.87
     longer
    0.86
    cium
    0.68
    maxwell
    0.68
     Ago
    0.68
    OOK
    0.68
     hiatus
    0.67
     sake
    0.67
    iatus
    0.65
    etheless
    0.65
    Act Density 0.025%

    No Known Activations