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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "train" or variations related to trains

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     estratégico
    -0.62
     flota
    -0.60
     niebla
    -0.59
     plegable
    -0.59
     Erwartungen
    -0.58
     stratégique
    -0.57
     Decke
    -0.57
     Aufklärung
    -0.57
     oposición
    -0.57
    ungkapkan
    -0.57
    POSITIVE LOGITS
     Train
    0.69
     train
    0.66
     Trains
    0.64
     tra
    0.64
    Personensuche
    0.59
     nut
    0.58
    HasAnnotation
    0.57
     Trained
    0.55
     Wifi
    0.54
     Css
    0.54
    Act Density 0.690%

    No Known Activations