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

    Neuronpedia

    INDEX
    Explanations

    references to raw materials or substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     targeted
    -0.58
    PathVariable
    -0.56
    ercises
    -0.55
     targeting
    -0.55
     autonomia
    -0.54
     definit
    -0.53
    drawiam
    -0.53
     damskie
    -0.53
    zcze
    -0.52
     monaster
    -0.52
    POSITIVE LOGITS
     raw
    1.15
     Raw
    1.10
    Raw
    0.95
     RAW
    0.85
     blades
    0.78
     grains
    0.76
     grain
    0.75
     blade
    0.73
     owed
    0.73
     Grain
    0.72
    Act Density 0.043%

    No Known Activations