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

    Neuronpedia

    INDEX
    Explanations

    transitional words and phrases that indicate additions or comparisons in text

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

    introducing additional information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.64
     betweenstory
    -0.50
    CloseOperation
    -0.49
    tanleria
    -0.48
    Билгалдахарш
    -0.48
    EndGlobal
    -0.46
    ↩
    -0.45
    気
    -0.44
    bcryptjs
    -0.44
    runge
    -0.43
    POSITIVE LOGITS
     also
    0.71
     lisäksi
    0.69
     Ebenso
    0.67
     additionally
    0.66
     likewise
    0.66
     همچنین
    0.65
     inoltre
    0.65
     також
    0.64
     asimismo
    0.64
     ayrıca
    0.63
    Act Density 0.095%

    No Known Activations