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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and their variations in context

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

    rather than, consequent to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lipa
    -0.59
     camar
    -0.55
     Jefus
    -0.55
     néglig
    -0.51
     purpoſe
    -0.50
     camara
    -0.50
     pinta
    -0.50
     tuc
    -0.50
    blauch
    -0.49
     bols
    -0.48
    POSITIVE LOGITS
    而
    1.89
     而
    1.49
    而在
    1.25
    而不
    0.82
    而出
    0.79
    而又
    0.71
    ⽽
    0.66
     sedangkan
    0.61
    而成
    0.61
    而去
    0.59
    Act Density 0.002%

    No Known Activations