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

    Neuronpedia

    INDEX
    Explanations

    studies that present research findings

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating research findings or results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     glide
    -0.71
     haircut
    -0.69
     veto
    -0.68
     choking
    -0.68
     grocer
    -0.65
     retaliate
    -0.64
    tall
    -0.64
     capit
    -0.63
     topp
    -0.63
     toast
    -0.61
    POSITIVE LOGITS
     studying
    1.04
     studies
    0.92
     universities
    0.89
    Study
    0.89
     conducted
    0.88
     professors
    0.87
     analys
    0.86
    earcher
    0.86
    research
    0.85
     academics
    0.85
    Act Density 0.419%

    No Known Activations