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

    references to helicopters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tle
    -0.89
    furt
    -0.89
    reads
    -0.79
    tg
    -0.78
    Ö¼
    -0.78
    女
    -0.77
    Detailed
    -0.74
    âĶģ
    -0.74
    orian
    -0.74
    gets
    -0.74
    POSITIVE LOGITS
     helicopters
    1.22
     helicopter
    1.21
     Helic
    1.04
     parach
    0.98
     helic
    0.98
     hangar
    0.94
     corps
    0.92
     hovering
    0.91
     skiing
    0.89
     helicop
    0.89
    Act Density 0.020%

    No Known Activations