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

    Neuronpedia

    INDEX
    Explanations

    concepts related to hidden elements or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     بيها
    -0.62
    WindowConstants
    -0.57
    iented
    -0.56
     Diz
    -0.56
     CWE
    -0.55
    setVerticalGroup
    -0.54
    illants
    -0.53
     aload
    -0.52
     diaphragm
    -0.52
    AdapterView
    -0.51
    POSITIVE LOGITS
     hid
    0.92
     hiding
    0.89
     hide
    0.89
     Hidden
    0.88
     hidden
    0.88
    MethodManager
    0.88
    HIDDEN
    0.85
     secret
    0.85
     behind
    0.84
     Hiding
    0.82
    Act Density 0.242%

    No Known Activations