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

    Neuronpedia

    INDEX
    Explanations

    repetitive phrases that indicate importance or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     overall
    -0.66
    overall
    -0.63
     Overall
    -0.57
     zweier
    -0.57
    Overall
    -0.57
     kokona
    -0.56
    styleType
    -0.56
    SourceChecksum
    -0.52
     another
    -0.52
     الحره
    -0.50
    POSITIVE LOGITS
     demás
    0.67
     stuff
    0.64
     paraphernalia
    0.63
     ingredients
    0.57
     aspects
    0.56
     things
    0.54
    SBATCH
    0.52
     remaining
    0.52
     facets
    0.52
     powy
    0.51
    Act Density 0.383%

    No Known Activations