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

    Neuronpedia

    INDEX
    Explanations

    phrases related to health and well-being

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to significant social issues and concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çīĪ
    -0.95
    luaj
    -0.75
    Ur
    -0.72
    ells
    -0.70
    OOD
    -0.65
    books
    -0.65
     belts
    -0.62
    Tim
    -0.62
     viz
    -0.62
     Libraries
    -0.62
    POSITIVE LOGITS
     prerequisite
    0.87
     commodity
    0.86
     factor
    0.84
     thing
    0.84
     predictor
    0.84
     symptom
    0.84
     cornerstone
    0.82
     Chaser
    0.81
     staple
    0.80
     hallmark
    0.79
    Act Density 0.297%

    No Known Activations