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

    Neuronpedia

    INDEX
    Explanations

    conjunctions that introduce contrasting or contradictory statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     lisäksi
    -0.68
     invece
    -0.68
     natomiast
    -0.67
     dagegen
    -0.62
     culoare
    -0.60
     zaś
    -0.60
     tillegg
    -0.59
     inoltre
    -0.59
    While
    -0.59
     entanto
    -0.58
    POSITIVE LOGITS
     also
    1.43
     anche
    1.11
     auch
    1.05
    also
    1.03
     גם
    0.97
     también
    0.97
     também
    0.91
    principalColumn
    0.91
    NameInMap
    0.90
     også
    0.85
    Act Density 0.118%

    No Known Activations