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

    Neuronpedia

    INDEX
    Explanations

    quantities and measurements related to time and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dalton
    -0.16
    vil
    -0.15
    fern
    -0.15
    ãĤĩ
    -0.15
    ippi
    -0.14
     vej
    -0.14
    ãģĹãĤĩ
    -0.14
    esis
    -0.13
    urat
    -0.13
    eln
    -0.13
    POSITIVE LOGITS
     reserved
    0.72
     dedicated
    0.63
     devoted
    0.63
    reserved
    0.57
     Reserved
    0.55
     reserve
    0.54
    Reserved
    0.50
     Dedicated
    0.50
     RESERVED
    0.49
     dedicate
    0.48
    Act Density 0.234%

    No Known Activations