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

    Neuronpedia

    INDEX
    Explanations

    negatively phrased statements or negative sentiments

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

    food and cooking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     avenir
    -0.46
     dezelve
    -0.42
     nødven
    -0.39
     giuri
    -0.39
     arbejde
    -0.39
     dår
    -0.38
    spyOn
    -0.38
     vicenda
    -0.37
    Бележки
    -0.37
     toekomst
    -0.37
    POSITIVE LOGITS
    EDEFAULT
    0.52
     gourmet
    0.52
     😋
    0.51
     pulumi
    0.50
     sauces
    0.50
     grills
    0.50
     soups
    0.50
     barbecue
    0.49
     cooks
    0.48
    IsMutable
    0.47
    Act Density 0.022%

    No Known Activations