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

    Neuronpedia

    INDEX
    Explanations

    references to various camps with numbers in their names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or places, particularly those named "Camp."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.84
     regress
    -0.69
     prob
    -0.67
     groom
    -0.64
    ulously
    -0.64
     magnification
    -0.60
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.60
     accelerator
    -0.59
    BLIC
    -0.59
     streak
    -0.58
    POSITIVE LOGITS
    agna
    1.23
    ground
    1.16
    agne
    1.15
    aign
    1.12
    bell
    1.07
    sites
    1.02
    fires
    0.95
    fire
    0.95
    grounds
    0.94
    ing
    0.88
    Act Density 0.025%

    No Known Activations