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

    Neuronpedia

    INDEX
    Explanations

    words related to technology and automation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to technology and automation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.97
    weak
    -0.75
    canon
    -0.71
    NAS
    -0.70
    wrong
    -0.69
    struction
    -0.66
     Yesterday
    -0.66
    major
    -0.65
     Ending
    -0.64
    fell
    -0.64
    POSITIVE LOGITS
     discreet
    0.85
     autonom
    0.83
     customized
    0.80
     LEDs
    0.79
     LED
    0.79
     pods
    0.78
     capsules
    0.76
     electricity
    0.76
     whichever
    0.76
     inhal
    0.76
    Act Density 0.922%

    No Known Activations