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

    Neuronpedia

    INDEX
    Explanations

    mentions of helicopters

    oai_token-act-pair · gpt-3.5-turbo

    mentions of helicopters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    furt
    -0.88
    heimer
    -0.82
    女
    -0.82
    tle
    -0.82
    âĶģ
    -0.79
    ql
    -0.79
    places
    -0.76
    Ö¼
    -0.76
    ãĥ´
    -0.75
    reads
    -0.75
    POSITIVE LOGITS
     helicopters
    1.10
     helicopter
    1.06
     hangar
    0.89
     parach
    0.88
     helic
    0.88
     corps
    0.87
     helicop
    0.87
     Helic
    0.87
     squadron
    0.87
     hovering
    0.86
    Act Density 0.020%

    No Known Activations