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

    Neuronpedia

    INDEX
    Explanations

    questions and statements about engagement and interactions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.70
    ⓧ
    -0.63
    almost
    -0.63
    Очень
    -0.62
    principalColumn
    -0.62
    DebuggerNonUser
    -0.62
    IUrlHelper
    -0.60
    PreferredItem
    -0.60
    AddField
    -0.60
     Tapatalk
    -0.60
    POSITIVE LOGITS
     how
    0.86
     poszczegól
    0.85
    哪些
    0.82
    บ้าง
    0.82
     each
    0.79
     versus
    0.77
     what
    0.77
     ulike
    0.75
     qué
    0.72
     कौन
    0.72
    Act Density 0.492%

    No Known Activations