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

    Neuronpedia

    INDEX
    Explanations

    concepts related to moral philosophy and the value of life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idata
    -0.15
    Pipeline
    -0.14
     CascadeType
    -0.14
    ribbon
    -0.14
    ãĤŃãĥ¥
    -0.14
    Documentation
    -0.14
     Aviation
    -0.14
    avax
    -0.13
    bulan
    -0.13
    ioni
    -0.13
    POSITIVE LOGITS
     Bent
    0.37
     Util
    0.34
     util
    0.33
     Raw
    0.31
     utility
    0.30
     Kant
    0.28
    Util
    0.27
     Utility
    0.27
     UTIL
    0.27
     Mill
    0.26
    Act Density 0.060%

    No Known Activations