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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "determine" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.69
    WhiteSpace
    -0.65
     Houſe
    -0.64
    Passenger
    -0.63
     newUser
    -0.63
    Space
    -0.63
     whitespace
    -0.63
    Spacing
    -0.62
    Spaces
    -0.61
    abancı
    -0.61
    POSITIVE LOGITS
     determine
    1.06
     Determine
    1.02
    determine
    1.00
     determined
    0.99
    Determine
    0.95
     determination
    0.94
     DETERMIN
    0.90
     determining
    0.89
     determines
    0.87
     Determined
    0.85
    Act Density 0.075%

    No Known Activations