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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise and strong opinions about experiences or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     uniquement
    -0.57
    ]-->
    -0.56
     betrekking
    -0.55
     algemeen
    -0.52
    もちろん
    -0.52
    勿論
    -0.52
     primarily
    -0.49
     především
    -0.49
    equalsIgnoreCase
    -0.49
     toepassing
    -0.48
    POSITIVE LOGITS
    GEBURTSDATUM
    0.84
     indeed
    0.80
     huh
    0.78
    VIAF
    0.77
    TypedDataSet
    0.77
    还真是
    0.76
    aarrggbb
    0.74
     sacré
    0.73
     '\\;'
    0.72
     Impressive
    0.71
    Act Density 0.173%

    No Known Activations