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

    Neuronpedia

    INDEX
    Explanations

    instances of action and advocacy related to social issues

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

    that modify other words

    np_acts-logits-general · gemini-2.0-flash

    consequence or continuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nemlig
    -0.62
     totiž
    -0.60
     nämlich
    -0.60
    évaluateur
    -0.59
     >=",
    -0.58
    such
    -0.57
     चीज़ों
    -0.57
     jednak
    -0.56
     Such
    -0.54
    this
    -0.54
    POSITIVE LOGITS
     therefrom
    1.07
     consiguiente
    1.03
     importantly
    0.98
     therefor
    0.94
     thereon
    0.94
     thereafter
    0.91
     dermed
    0.91
    何より
    0.89
     accordingly
    0.89
     daarbij
    0.86
    Act Density 0.715%

    No Known Activations