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

    Neuronpedia

    INDEX
    Explanations

    terms related to non-typical or negative descriptors in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     most
    -0.45
    most
    -0.40
     certainly
    -0.38
     decote
    -0.38
    BagLayout
    -0.34
     correcto
    -0.33
    kannt
    -0.33
     camada
    -0.33
     olan
    -0.33
     Wohl
    -0.32
    POSITIVE LOGITS
    httphttps
    0.66
     '\\;'
    0.59
    出版年
    0.59
     saites
    0.58
     refundable
    0.58
    onsense
    0.57
    #
    0.56
    ancourt
    0.55
     estekak
    0.54
     kaarangay
    0.54
    Act Density 0.255%

    No Known Activations