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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate causal relationships or conditions

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

    Prepositions "of", "to", or "due" followed by "the"

    np_acts-logits-general · gemini-2.0-flash

    because of / due to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mô
    -0.54
     Púb
    -0.53
    ніципалі
    -0.51
    herself
    -0.50
     fieldNum
    -0.48
     Cæsar
    -0.47
     itſelf
    -0.47
     виправи
    -0.47
    outState
    -0.46
    nasium
    -0.46
    POSITIVE LOGITS
     lack
    1.09
     fehl
    0.79
     kasarigan
    0.79
    lack
    0.79
     adanya
    0.72
     its
    0.72
     reasons
    0.71
     fear
    0.70
     lacking
    0.70
     gebre
    0.69
    Act Density 0.298%

    No Known Activations