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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expectations and feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ordinaires
    -0.77
     convenable
    -0.74
     sû
    -0.74
     sortes
    -0.73
     quelcon
    -0.70
     vostra
    -0.69
     ordinaire
    -0.69
     spéciaux
    -0.65
     spéciale
    -0.65
     quelquefois
    -0.65
    POSITIVE LOGITS
     leveraging
    0.88
     proactively
    0.81
     CreateTagHelper
    0.79
     leveraged
    0.76
     prior
    0.75
    UpInside
    0.71
     impactful
    0.71
     incremental
    0.69
     summarized
    0.68
    NameInMap
    0.68
    Act Density 0.085%

    No Known Activations