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

    Neuronpedia

    INDEX
    Explanations

    negative phrases and concepts related to expectations and limitations

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

    following prepositions

    np_acts-logits-general · gemini-2.0-flash

    describing states or qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.53
    ༘
    -0.46
    цезда
    -0.42
     Wicidata
    -0.39
     Numerade
    -0.38
    馃
    -0.37
    aimer
    -0.37
     objet
    -0.35
    featureID
    -0.35
    المشاركات
    -0.34
    POSITIVE LOGITS
     AssemblyTitle
    0.61
    TagMode
    0.57
    shortcuts
    0.54
     stereotypical
    0.48
     superficial
    0.46
     stereotyp
    0.45
     silos
    0.45
     unrealistic
    0.45
     hierarchical
    0.45
     rigidity
    0.45
    Act Density 0.348%

    No Known Activations