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

    Neuronpedia

    INDEX
    Explanations

    physical holes or openings in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to physical openings or gaps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStream
    -0.81
    soDeliveryDate
    -0.80
    APH
    -0.78
    tesy
    -0.75
    HCR
    -0.74
    Percent
    -0.72
    urdue
    -0.72
    RESULTS
    -0.71
    trak
    -0.70
    rection
    -0.69
    POSITIVE LOGITS
     fabric
    1.49
     walls
    1.34
     bedrock
    1.28
     limestone
    1.25
     flesh
    1.20
     hull
    1.19
     membrane
    1.16
     membranes
    1.16
     layers
    1.14
     facade
    1.14
    Act Density 0.204%

    No Known Activations