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

    Neuronpedia

    INDEX
    Explanations

    the presence of special tokens indicating document boundaries or structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kaarangay
    -0.79
    SourceChecksum
    -0.73
    IsContent
    -0.68
     MenuView
    -0.68
    Népesség
    -0.64
    batore
    -0.62
    ьаж
    -0.61
    contentLoaded
    -0.60
     Fait
    -0.59
    NameInMap
    -0.59
    POSITIVE LOGITS
    Portail
    0.75
     تانيه
    0.66
    Портал
    0.56
    tvguidetime
    0.55
    קישורים
    0.54
     يتيمه
    0.51
    nmgp
    0.51
    scriptcase
    0.51
    ποτε
    0.50
    atguigu
    0.50
    Act Density 0.005%

    No Known Activations