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

    Neuronpedia

    INDEX
    Explanations

    descriptors and classifications related to attributes and patterns in dietary and personality contexts

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

    types of personalities or behaviors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     plezier
    -0.37
     semakin
    -0.35
    verifyException
    -0.31
     INSTRUCTIONS
    -0.31
    ativement
    -0.30
     nachdem
    -0.30
     Instructions
    -0.30
    Atsauces
    -0.30
     sebaik
    -0.30
    ぜひ
    -0.30
    POSITIVE LOGITS
     فريبيس
    0.67
     ThemeData
    0.57
     للمعارف
    0.54
    aarrggbb
    0.52
    Datuak
    0.51
    RTEX
    0.50
    RTLR
    0.49
     allAfrica
    0.48
    ricos
    0.48
    saraba
    0.48
    Act Density 0.021%

    No Known Activations