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

    Neuronpedia

    INDEX
    Explanations

    mentions of battery-related terms and technologies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     intermitt
    -0.80
     michelin
    -0.77
     desir
    -0.77
     casio
    -0.76
     seiz
    -0.76
     accla
    -0.75
     reconno
    -0.74
     madonna
    -0.74
     vhs
    -0.74
     scrat
    -0.74
    POSITIVE LOGITS
     battery
    1.47
     batteries
    1.32
    battery
    1.30
     Battery
    1.30
    Battery
    1.26
     Batteries
    1.14
     BATTERY
    1.03
    Batteries
    0.96
    BATTERY
    0.88
     bater
    0.86
    Act Density 0.056%

    No Known Activations