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

    Neuronpedia

    INDEX
    Explanations

    terms related to machine learning algorithms and model evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.66
    GEBURTSDATUM
    -0.57
    AsUp
    -0.55
    ")));
    -0.55
    forChild
    -0.52
     transfieras
    -0.52
     }</
    -0.50
    })();
    -0.50
     ''){
    -0.50
     actionMode
    -0.49
    POSITIVE LOGITS
    IntoConstraints
    0.44
     boosting
    0.41
    GMENT
    0.39
     consciously
    0.36
    platform
    0.35
     training
    0.35
     bewust
    0.35
     sessionFactory
    0.34
    training
    0.34
     boost
    0.33
    Act Density 0.955%

    No Known Activations