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

    Neuronpedia

    INDEX
    Explanations

    instances of code or comments in programming contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    straints
    -0.68
    ✨:
    -0.67
    tvguidetime
    -0.66
     domestiques
    -0.66
     Lindgren
    -0.66
     słon
    -0.64
     africains
    -0.63
    verhältnis
    -0.63
     étan
    -0.63
     strengths
    -0.61
    POSITIVE LOGITS
    ArgumentParser
    0.62
    ști
    0.60
     nonatomic
    0.60
    rmtree
    0.59
     antig
    0.58
    </i>
    0.57
    xtext
    0.57
    CardBody
    0.55
     ExecuteAsync
    0.54
     firebaseConfig
    0.54
    Act Density 0.005%

    No Known Activations