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

    Neuronpedia

    INDEX
    Explanations

    numerical values associated with various data types or properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    st
    -0.49
     Humphreys
    -0.49
    <h1>
    -0.49
     Schre
    -0.47
     McDonough
    -0.46
     Schne
    -0.46
     under
    -0.46
    9
    -0.46
     Schrö
    -0.46
    not
    -0.45
    POSITIVE LOGITS
     Value
    1.25
     VALUE
    1.16
     value
    1.13
    Value
    1.13
    value
    1.05
     getValue
    1.04
     Values
    1.04
    VALUE
    1.00
     valu
    0.98
    ValueStyle
    0.93
    Act Density 0.184%

    No Known Activations