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

    Neuronpedia

    INDEX
    Explanations

    references to scientific studies or research

    oai_token-act-pair · gpt-3.5-turbo

    references to scientific studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.65
    cream
    -0.62
     Reyn
    -0.60
     helic
    -0.60
    entity
    -0.59
     resonance
    -0.58
     champagne
    -0.57
     bonded
    -0.55
     inert
    -0.55
    cycl
    -0.55
    POSITIVE LOGITS
    udo
    0.87
    study
    0.86
    ador
    0.80
    UF
    0.80
    Study
    0.79
    iveness
    0.77
     methodology
    0.77
    ļéĨĴ
    0.76
     study
    0.74
     findings
    0.71
    Act Density 0.031%

    No Known Activations