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

    Neuronpedia

    INDEX
    Explanations

    phrases related to causation and consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AutoField
    -0.43
    gäng
    -0.42
    hmen
    -0.41
    LayoutPanel
    -0.40
    前后
    -0.39
    Попис
    -0.37
    MultipartFile
    -0.36
    -0.36
    parsedMessage
    -0.36
    utnant
    -0.35
    POSITIVE LOGITS
     further
    2.77
     farther
    2.53
    further
    2.50
    Further
    2.34
     Further
    2.27
     FURTHER
    2.23
    FURTHER
    1.90
     weiter
    1.73
     furthest
    1.62
     дальше
    1.56
    Act Density 0.879%

    No Known Activations