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

    Neuronpedia

    INDEX
    Explanations

    descriptions of physical dirt

    oai_token-act-pair · gpt-3.5-turbo

    references to dirt in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orial
    -0.72
    sych
    -0.69
     CrossRef
    -0.67
    mental
    -0.65
    card
    -0.63
     Mult
    -0.63
     Programme
    -0.62
     Management
    -0.61
     Pulse
    -0.61
     Languages
    -0.61
    POSITIVE LOGITS
     dirt
    3.86
     Dirt
    2.46
     gravel
    1.73
     mud
    1.59
     dirty
    1.52
     asphalt
    1.33
     dust
    1.30
    dirty
    1.28
     dusty
    1.24
     filthy
    1.18
    Act Density 0.006%

    No Known Activations