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

    Neuronpedia

    INDEX
    Explanations

    instances where being part of a group, conversation, solution, or program is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    references to being part of a group, conversation, or community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stasy
    -0.65
    asu
    -0.61
     heights
    -0.58
     appre
    -0.58
     millenn
    -0.55
     ceilings
    -0.55
    icon
    -0.54
    rame
    -0.53
     Agenda
    -0.53
     surprises
    -0.52
    POSITIVE LOGITS
    aking
    1.07
    ridge
    0.95
    quartered
    0.80
    ook
    0.79
    aken
    0.79
    ridges
    0.78
    ying
    0.78
     of
    0.78
    nered
    0.78
    akers
    0.77
    Act Density 0.032%

    No Known Activations