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

    Neuronpedia

    INDEX
    Explanations

    terms expressing value and importance in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ViewFeatures
    -0.96
     Pharisees
    -0.76
     penit
    -0.74
    pyplot
    -0.72
     Phari
    -0.71
    Chham
    -0.70
    ResponseWriter
    -0.69
    writeHead
    -0.69
    HasBeenSet
    -0.68
    Out
    -0.68
    POSITIVE LOGITS
     cherished
    1.20
     treasured
    1.12
     valued
    1.06
     cherish
    0.95
     precious
    0.95
    treasure
    0.93
     Precious
    0.90
     beloved
    0.85
    Precious
    0.82
    precious
    0.82
    Act Density 0.156%

    No Known Activations