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

    Neuronpedia

    INDEX
    Explanations

    references to significant events or topics labeled as "major."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Evaporation
    -0.57
     pellic
    -0.54
     Envelope
    -0.54
     nanotubes
    -0.53
    thebibliography
    -0.52
     Cube
    -0.51
     sval
    -0.50
     lingual
    -0.49
     selfie
    -0.49
     geografic
    -0.49
    POSITIVE LOGITS
     major
    1.66
    major
    1.66
    Major
    1.52
     Major
    1.49
     MAJOR
    1.48
    MAJOR
    1.42
     Majors
    1.09
     majors
    1.06
     majeurs
    0.93
    minor
    0.91
    Act Density 0.103%

    No Known Activations