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

    Neuronpedia

    INDEX
    Explanations

    terms related to theft, loss, and missing items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     informée
    -0.62
    хьтан
    -0.59
    脚注の使い方
    -0.56
    umumkan
    -0.53
    揉
    -0.51
     snippetHide
    -0.51
    imageshack
    -0.50
     المعيارى
    -0.49
    verifyException
    -0.49
     Italijanski
    -0.49
    POSITIVE LOGITS
     missing
    0.79
     absent
    0.67
     loss
    0.66
     Missing
    0.64
    Gone
    0.60
     lost
    0.57
     disappeared
    0.57
    absent
    0.56
    Missing
    0.55
     disappearance
    0.55
    Act Density 0.881%

    No Known Activations