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

    Neuronpedia

    INDEX
    Explanations

    instances of significant metrics or comparisons in data reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     apparently
    -0.59
     surely
    -0.53
     absolutely
    -0.52
     undoubtedly
    -0.52
     assolutamente
    -0.51
     absolutamente
    -0.50
     ternyata
    -0.49
     nämlich
    -0.49
     sicherlich
    -0.49
     certainement
    -0.48
    POSITIVE LOGITS
     متعلقه
    0.89
    GOTREF
    0.86
     CURIAM
    0.84
    colgroup
    0.81
     unknownFields
    0.81
    EndInit
    0.80
     sorta
    0.78
     like
    0.77
    tagext
    0.76
     "..\..\..\
    0.74
    Act Density 0.108%

    No Known Activations