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

    Neuronpedia

    INDEX
    Explanations

    phrases referring to accountability and legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EndInit
    -0.85
    MessageTagHelper
    -0.84
    Personendaten
    -0.84
     pleaſure
    -0.82
    Diweddarwch
    -0.81
     houſe
    -0.77
     ſta
    -0.76
    principalTable
    -0.75
    最快更新
    -0.74
    ViewFeatures
    -0.74
    POSITIVE LOGITS
    AddHtmlAttribute
    0.50
     notamment
    0.49
     than
    0.45
     שוליים
    0.45
    着一
    0.44
     of
    0.43
     estekak
    0.42
     primarily
    0.40
    łę
    0.36
     oma
    0.36
    Act Density 0.613%

    No Known Activations