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

    Neuronpedia

    INDEX
    Explanations

    mentions of power sources or energy supplies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    esan
    -1.02
    apeake
    -0.92
    ordan
    -0.88
    ylum
    -0.87
    alon
    -0.83
    EMS
    -0.82
     Nationals
    -0.81
    essors
    -0.80
     Leaves
    -0.79
     Heights
    -0.79
    POSITIVE LOGITS
    packs
    0.95
    escape
    0.85
    ItemTracker
    0.84
    kamp
    0.84
    flation
    0.83
    PDATE
    0.80
    ggle
    0.78
     handc
    0.77
    loop
    0.77
    pread
    0.76
    Act Density 0.558%

    No Known Activations