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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that emphasize the duality of benefits and drawbacks in various situations

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

    after positive-sentiment words

    np_acts-logits-general · gemini-2.0-flash

    positive attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SwingConstants
    -0.40
     humaine
    -0.40
    sitis
    -0.40
    viewType
    -0.40
    TagMode
    -0.38
    ExtendWith
    -0.36
    CppMethod
    -0.35
     uczniów
    -0.34
     gait
    -0.34
    hadiran
    -0.34
    POSITIVE LOGITS
     nahilalakip
    0.65
    featureID
    0.53
     favourably
    0.49
     favorably
    0.48
    PREFERRED
    0.48
    ActionButton
    0.48
     praised
    0.47
    onomía
    0.47
     advantageous
    0.46
    advantages
    0.46
    Act Density 1.949%

    No Known Activations