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

    Neuronpedia

    INDEX
    Explanations

    references to co-authorship or collaborative work in legal documents

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     الرياضيه
    -0.75
    HtmlAttribute
    -0.72
    #+#
    -0.71
     imageNamed
    -0.68
     محفوظة
    -0.66
    AxisAlignment
    -0.66
    قایناقلار
    -0.66
    EndContext
    -0.66
     InputDecoration
    -0.65
    قایناق‌لار
    -0.65
    POSITIVE LOGITS
    ilación
    0.59
    petual
    0.54
    tits
    0.51
     excu
    0.48
     Advance
    0.47
    互联网档案馆
    0.47
    guan
    0.47
    Bun
    0.47
     recevrez
    0.47
    enken
    0.46
    Act Density 0.005%

    No Known Activations