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

    Neuronpedia

    INDEX
    Explanations

    words related to a change or development in a process

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "come to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hierarch
    -0.66
    llan
    -0.66
     conveyed
    -0.59
     Direction
    -0.59
    Rocket
    -0.58
     Advertisement
    -0.57
     Onion
    -0.57
     quot
    -0.56
     willpower
    -0.56
     incoming
    -0.56
    POSITIVE LOGITS
     grips
    1.11
     fruition
    1.10
     prominence
    0.96
     blows
    0.83
     conclusions
    0.81
     dominate
    0.80
     fray
    0.72
    asted
    0.70
    ying
    0.70
    redit
    0.69
    Act Density 0.070%

    No Known Activations