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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "edit" and its variations, indicating a focus on modifications or revisions within the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Hochspringen
    -0.55
    ."</
    -0.53
     McLean
    -0.53
     Lena
    -0.52
    }{$\
    -0.52
    </>
    -0.52
    DTD
    -0.52
     Kras
    -0.52
     tr
    -0.51
     Signalez
    -0.51
    POSITIVE LOGITS
    fjspx
    0.58
     Vikipedi
    0.56
    enschappelijke
    0.56
    AddHtmlAttribute
    0.54
    TestingModule
    0.52
     саны
    0.51
    UpDown
    0.50
     Wikipédia
    0.50
    jspx
    0.49
    providedIn
    0.49
    Act Density 0.002%

    No Known Activations