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

    Neuronpedia

    INDEX
    Explanations

    intensifiers or adverbs that express sincerity or authenticity

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

    truly followed by affirmation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     հղումներ
    -0.59
     fubject
    -0.56
    Seam
    -0.52
     vege
    -0.52
     heretics
    -0.51
     cops
    -0.50
    fromCharCode
    -0.47
    Sink
    -0.47
    spam
    -0.47
     newList
    -0.47
    POSITIVE LOGITS
     truly
    1.46
    truly
    1.34
    Truly
    1.28
     Truly
    1.27
     verdaderamente
    0.98
     genuinely
    0.90
     gerçekten
    0.75
     deeply
    0.70
     veramente
    0.66
     sincerely
    0.65
    Act Density 0.003%

    No Known Activations