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

    Neuronpedia

    INDEX
    Explanations

    terms related to color as well as directions in space

    oai_token-act-pair · gpt-3.5-turbo

    terms relating to physical attributes and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chwitz
    -0.81
    Nation
    -0.77
    DEM
    -0.71
    recent
    -0.71
    HCR
    -0.71
    Recent
    -0.70
    ;;;;
    -0.69
    galitarian
    -0.68
     Posted
    -0.65
    ARB
    -0.63
    POSITIVE LOGITS
     portion
    1.50
     component
    1.12
     portions
    1.11
     element
    1.07
     bits
    1.04
     aspect
    1.03
     part
    1.01
     itself
    1.00
     layer
    0.99
     halves
    0.97
    Act Density 0.373%

    No Known Activations