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
    女
    -0.83
    ãĥ´
    -0.82
    heimer
    -0.80
    âĶģ
    -0.79
    furt
    -0.79
    topic
    -0.78
    ql
    -0.77
    tle
    -0.77
    Ö¼
    -0.76
    orian
    -0.75
    POSITIVE LOGITS
     helicopters
    1.08
     helicopter
    1.06
     helicop
    0.89
     parach
    0.87
     hangar
    0.87
     blades
    0.87
     pilots
    0.87
     hovering
    0.86
     flown
    0.85
     swoop
    0.84
    Act Density 0.026%

    No Known Activations