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

    Neuronpedia

    INDEX
    Explanations

    concepts related to beliefs, intentions, and legal considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <h5>
    -0.47
    SourceChecksum
    -0.46
    ρίου
    -0.44
    agn
    -0.41
    europa
    -0.41
    OneToMany
    -0.40
    Predecesor
    -0.39
    xlarge
    -0.39
    asc
    -0.39
     Courtesy
    -0.38
    POSITIVE LOGITS
    AddTagHelper
    0.90
    enuine
    0.74
    genu
    0.71
     sincerely
    0.71
    RectangleBorder
    0.69
     invokingState
    0.66
     contextLoads
    0.66
    MLLoader
    0.65
    0.64
     propOrder
    0.64
    Act Density 0.386%

    No Known Activations