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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and notations, particularly related to equations and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ::::::::
    -0.54
    ạn
    -0.48
     van
    -0.47
    XmlType
    -0.47
     ativ
    -0.46
    olition
    -0.45
     utafiti
    -0.44
     [*]
    -0.44
    urably
    -0.44
    แล้ว
    -0.44
    POSITIVE LOGITS
     myſelf
    0.87
     itſelf
    0.83
     himſelf
    0.74
     houſe
    0.73
     themſelves
    0.73
     juſ
    0.71
     chofe
    0.71
     EnglishChoose
    0.70
     reaſon
    0.65
     titolata
    0.65
    Act Density 1.655%

    No Known Activations