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

    Neuronpedia

    INDEX
    Explanations

    references to significant or important concepts, often indicated by the word "major."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ']?>
    -0.68
    ']}
    -0.67
     Fels
    -0.65
    </blockquote>
    -0.64
     }}$
    -0.63
    tik
    -0.61
    </i>
    -0.60
    )}=
    -0.59
    </em>
    -0.58
    وص
    -0.57
    POSITIVE LOGITS
    MAJOR
    1.43
     MAJOR
    1.42
    major
    1.37
     Majors
    1.37
     majors
    1.30
    Major
    1.27
     major
    1.26
     Major
    1.26
     Majefty
    1.16
    maj
    1.15
    Act Density 0.042%

    No Known Activations