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

    Neuronpedia

    INDEX
    Explanations

    interrogative and conditional phrases that relate to time or conditions

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

    time/condition conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    раздо
    -0.62
     spørs
    -0.61
     informée
    -0.57
    ंदीखरीदारी
    -0.56
     Waray
    -0.52
    ValueStyle
    -0.52
     kijang
    -0.50
    ことがある
    -0.49
     rumput
    -0.48
     gyhoeddwyd
    -0.48
    POSITIVE LOGITS
     onde
    0.58
     donde
    0.56
     dove
    0.56
     بينما
    0.48
     عندما
    0.48
     Donde
    0.48
    ":[{
    0.47
     günü
    0.47
    masını
    0.47
     grouse
    0.45
    Act Density 0.006%

    No Known Activations