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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating capability or ability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.76
    piecze
    -0.69
     متعلقه
    -0.66
     dares
    -0.65
    łaszcza
    -0.62
    testens
    -0.59
     समीक्षाएं
    -0.58
     laurels
    -0.58
    UnknownFieldSet
    -0.57
    seamnă
    -0.56
    POSITIVE LOGITS
     capable
    0.92
    capable
    0.81
     képes
    0.73
    unable
    0.72
     able
    0.72
     capaz
    0.67
     utilizing
    0.63
     capables
    0.63
     Able
    0.63
     capace
    0.62
    Act Density 0.446%

    No Known Activations