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

    Neuronpedia

    INDEX
    Explanations

    numerical values or numerical related terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     millenn
    -0.76
    ooks
    -0.76
    Īè
    -0.70
    egal
    -0.69
    wings
    -0.69
    ¯¯¯¯
    -0.68
    âĸ¬
    -0.68
     Citiz
    -0.68
    nesses
    -0.68
    dar
    -0.67
    POSITIVE LOGITS
     value
    0.85
     values
    0.80
    variable
    0.79
     stored
    0.79
     fluct
    0.74
     computed
    0.74
     (<
    0.74
     resistor
    0.71
     (.
    0.71
     thereof
    0.71
    Act Density 0.029%

    No Known Activations