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

    Neuronpedia

    INDEX
    Explanations

    phrases involving curiosity and inquiry

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.70
    bewerken
    -0.59
    Personendaten
    -0.57
    SourceChecksum
    -0.53
    principalTable
    -0.52
     autorytatywna
    -0.52
     externi
    -0.52
     дописавши
    -0.52
    -0.51
     TextAppearance
    -0.49
    POSITIVE LOGITS
    WebServlet
    0.59
    :][
    0.56
     chat
    0.56
     peg
    0.56
    remark
    0.54
    asts
    0.54
     remark
    0.54
     Comment
    0.53
     Peg
    0.53
     comment
    0.52
    Act Density 0.029%

    No Known Activations