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

    Neuronpedia

    INDEX
    Explanations

    technical terms or specific words related to technology or science

    oai_token-act-pair · gpt-3.5-turbo

    terms related to specific technical concepts or components, particularly in technology and science

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rencies
    -0.77
    urches
    -0.76
     Machines
    -0.70
    brids
    -0.67
    doms
    -0.67
    assies
    -0.65
    ernels
    -0.65
    lees
    -0.64
     Vehicles
    -0.63
    itars
    -0.63
    POSITIVE LOGITS
     standpoint
    0.77
     sized
    0.65
     statement
    0.61
    atical
    0.59
     variant
    0.59
     perspective
    0.59
     component
    0.58
     approximation
    0.58
    oser
    0.57
     version
    0.57
    Act Density 0.953%

    No Known Activations