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

    Neuronpedia

    INDEX
    Explanations

    expressions or actions related to showing respect or gratitude

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to celebration and respect

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resides
    -0.72
     stages
    -0.68
     sands
    -0.66
     motions
    -0.63
     mutated
    -0.63
     pedals
    -0.62
     poured
    -0.60
     molded
    -0.60
    borg
    -0.60
     Wer
    -0.59
    POSITIVE LOGITS
     confusion
    0.98
     misunder
    0.88
     confuse
    0.86
     discourage
    0.83
     coincidence
    0.80
     clarification
    0.79
    catentry
    0.79
     inconvenience
    0.78
    avoid
    0.78
     conflic
    0.78
    Act Density 0.723%

    No Known Activations