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

    Neuronpedia

    INDEX
    Explanations

    references to establishments or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sabotage
    -0.54
     Mee
    -0.52
     assassination
    -0.52
     rainy
    -0.51
    hia
    -0.51
     
    -0.51
    thâu
    -0.49
    f
    -0.49
    propTypes
    -0.49
     reserving
    -0.48
    POSITIVE LOGITS
     entity
    0.95
     entities
    0.92
     apparaat
    0.84
     device
    0.81
     vessel
    0.79
    licola
    0.78
     structures
    0.76
     institution
    0.74
     Kombat
    0.73
     devices
    0.72
    Act Density 0.860%

    No Known Activations