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

    Neuronpedia

    INDEX
    Explanations

    phrases or expressions indicating impossibility or inability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    statements of inability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    J
    -0.51
     lube
    -0.47
    riu
    -0.47
     stuff
    -0.46
    tie
    -0.46
    Stuff
    -0.45
    stuff
    -0.44
    ệu
    -0.44
    ie
    -0.44
     Stuff
    -0.44
    POSITIVE LOGITS
     cannot
    1.08
    Cannot
    1.02
     CANNOT
    1.01
    cannot
    1.01
     Cannot
    0.98
     canst
    0.76
    ihnach
    0.71
    DoNot
    0.68
     dapat
    0.66
     BrowserModule
    0.66
    Act Density 0.011%

    No Known Activations