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

    Neuronpedia

    INDEX
    Explanations

    mentions of "Hill" followed by a number similar to a news article section or reference

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or organization, primarily "Hill."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĹ¼
    -0.78
    ============
    -0.75
    ACTED
    -0.74
    glomer
    -0.70
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.67
    س
    -0.67
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.66
    razil
    -0.66
    uality
    -0.66
    Slot
    -0.65
    POSITIVE LOGITS
    iard
    1.18
     Hill
    0.94
    yer
    0.92
    side
    0.91
    top
    0.89
    castle
    0.85
    boro
    0.84
    stones
    0.82
    hog
    0.81
    hill
    0.80
    Act Density 0.011%

    No Known Activations