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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "can't" or its variations, indicating inability or restriction

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

    can't + verb indicating inability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.72
     raiſ
    -0.61
     ſtate
    -0.60
     houſe
    -0.58
     fubject
    -0.57
     purpoſe
    -0.56
    wapV
    -0.52
     myſelf
    -0.51
     nodeId
    -0.50
     Chriftian
    -0.49
    POSITIVE LOGITS
     cant
    1.58
     Cant
    1.37
    Cant
    1.30
    cant
    1.29
     CANT
    1.20
    CANT
    0.99
     wont
    0.92
     aint
    0.75
     couldnt
    0.74
     isnt
    0.72
    Act Density 0.007%

    No Known Activations