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

    Neuronpedia

    INDEX
    Explanations

    a diverse range of research-related contexts and sample populations

    oai_token-act-pair · gpt-3.5-turbo

    quantitative data related to surveys or population studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    danger
    -0.73
     Nib
    -0.70
     pus
    -0.69
    redo
    -0.69
    THING
    -0.67
    ror
    -0.66
    EXT
    -0.66
    ]=
    -0.66
    agy
    -0.65
    arde
    -0.65
    POSITIVE LOGITS
     sampled
    1.05
     randomized
    1.03
     randomly
    0.97
     surveyed
    0.92
     spanning
    0.87
     conducted
    0.86
     dataset
    0.85
     evaluated
    0.85
     enrolled
    0.84
     published
    0.84
    Act Density 0.391%

    No Known Activations