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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating preferences or desires

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    y
    -0.58
    .
    -0.55
    1
    -0.54
     are
    -0.49
     
    -0.48
    i
    -0.48
     lourd
    -0.47
     hígado
    -0.46
    5
    -0.46
    ↵↵
    -0.46
    POSITIVE LOGITS
    Portale
    1.29
     للمعارف
    1.21
     betweenstory
    1.13
     Мексичка
    1.09
    WireFormatLite
    1.08
     AssemblyTitle
    1.05
    ########.
    1.05
    ThroughAttribute
    1.04
    PMailer
    1.04
    writeFieldEnd
    1.03
    Act Density 0.747%

    No Known Activations