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

    Neuronpedia

    INDEX
    Explanations

    phrases related to gathering and addressing feedback from team members and external reviewers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     приготування
    -0.54
    놀
    -0.53
    matchCondition
    -0.52
    AddRef
    -0.50
    GEBURTSDATUM
    -0.49
     VizieR
    -0.47
     resourceCulture
    -0.47
     quarts
    -0.47
     torchvision
    -0.47
    apimachinery
    -0.47
    POSITIVE LOGITS
     feedback
    2.43
     Feedback
    2.02
    feedback
    1.96
    Feedback
    1.86
     feedbacks
    1.67
     FEEDBACK
    1.66
     input
    1.61
     suggestions
    1.60
     comments
    1.55
    FEEDBACK
    1.49
    Act Density 0.252%

    No Known Activations