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

    Neuronpedia

    INDEX
    Explanations

    the presence of "TODO" notations and variations of the word "strip" in a codebase

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ButterKnife
    -0.49
    +#+#
    -0.45
    Dobrý
    -0.40
    ennemi
    -0.35
     cucchiai
    -0.35
     tutkim
    -0.35
    CompleteListener
    -0.35
     związ
    -0.35
    keur
    -0.35
     preghi
    -0.34
    POSITIVE LOGITS
    todo
    0.79
     strip
    0.79
     Strip
    0.77
     todo
    0.76
     Todo
    0.75
    strip
    0.72
     STRIP
    0.71
     Profiles
    0.70
    Todo
    0.69
    TODO
    0.69
    Act Density 0.248%

    No Known Activations