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

    Neuronpedia

    INDEX
    Explanations

    references to household dynamics and decision-making roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InstrumentedTest
    -0.73
     CreateTagHelper
    -0.66
    :+:
    -0.65
     Nose
    -0.64
    didReceive
    -0.63
    endaft
    -0.61
     chair
    -0.59
    findpost
    -0.58
    WriteLiteral
    -0.58
    jutant
    -0.56
    POSITIVE LOGITS
     lines
    0.67
     vocal
    0.64
     Lines
    0.63
    Lines
    0.61
    lines
    0.60
    Nodes
    0.58
     vocales
    0.56
     moves
    0.55
     vocals
    0.54
    Referencie
    0.54
    Act Density 0.095%

    No Known Activations