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

    Neuronpedia

    INDEX
    Explanations

    negative constructions and expressions of disbelief or skepticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    toBe
    -0.65
    duire
    -0.60
     wären
    -0.58
    ieszcz
    -0.57
    Swift
    -0.57
     affaire
    -0.57
     Bande
    -0.56
     թվական
    -0.56
     varit
    -0.54
     merid
    -0.54
    POSITIVE LOGITS
     do
    0.96
    RegistryLite
    0.89
     DO
    0.89
    पया
    0.80
    AnchorStyles
    0.79
     does
    0.78
     Does
    0.77
    evsky
    0.77
    httphttps
    0.75
    XmlAccessType
    0.75
    Act Density 0.186%

    No Known Activations