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

    Neuronpedia

    INDEX
    Explanations

    expressions of hate or negative feelings toward various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     jurk
    -0.47
     reason
    -0.42
     doInBackground
    -0.41
     donnée
    -0.39
    ClientRect
    -0.39
     soeur
    -0.39
     diff
    -0.38
     Polly
    -0.38
    NonQuery
    -0.37
    wwww
    -0.37
    POSITIVE LOGITS
     Савезне
    0.91
     disambiguazione
    0.71
    homonymie
    0.61
     Biôgrafia
    0.60
     distancing
    0.60
     CanadaChoose
    0.59
     ujednoznacz
    0.57
     Италијани
    0.57
     Italijanski
    0.56
     Gemein
    0.56
    Act Density 0.205%

    No Known Activations