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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "proposal" and its variations indicating suggested plans or ideas

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     suggestion
    -0.85
     suggestions
    -0.84
     sugg
    -0.83
     suggested
    -0.79
     suggest
    -0.75
    Suggestion
    -0.73
     SUGGEST
    -0.73
     suggests
    -0.73
     Suggestion
    -0.73
    SUGGEST
    -0.73
    POSITIVE LOGITS
    complexContent
    0.93
     rospy
    0.84
    ViewFeatures
    0.82
    isabeth
    0.80
    dymyr
    0.79
    epy
    0.78
    fır
    0.78
    %%%%%%%%%%%%%%%%
    0.77
     Réponses
    0.77
     BGB
    0.77
    Act Density 0.024%

    No Known Activations