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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing magnitude or high intensity

    oai_token-act-pair · gpt-3.5-turbo

    intensifiers that describe popularity or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igi
    -0.75
    ensing
    -0.74
    ebin
    -0.72
    icip
    -0.70
    ties
    -0.67
    iem
    -0.67
    iture
    -0.66
    icipated
    -0.66
    oslov
    -0.65
     Continued
    -0.64
    POSITIVE LOGITS
     Important
    0.83
     underrated
    0.80
     profitable
    0.74
     beneficial
    0.74
     impractical
    0.73
     important
    0.70
     satisfying
    0.70
     rewarding
    0.69
     Awesome
    0.68
     fascinating
    0.68
    Act Density 0.049%

    No Known Activations