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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "unexpected"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.73
    
    -0.69
     Архів
    -0.66
    ']}
    -0.64
    исленность
    -0.61
    ')}
    -0.60
     mostrarán
    -0.59
     superintendents
    -0.58
     superintendent
    -0.58
    Superintendent
    -0.58
    POSITIVE LOGITS
     unexpectedly
    0.72
     no
    0.71
     unexpected
    0.71
     suddenly
    0.70
    ioutil
    0.70
    unexpected
    0.69
     late
    0.68
     Late
    0.66
     mourut
    0.66
     sudden
    0.65
    Act Density 0.156%

    No Known Activations