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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating assistance or support in various contexts

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

    with the help of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iség
    -0.42
    -0.42
    newtheorem
    -0.40
    AnimationsModule
    -0.40
    ptăm
    -0.39
    rådet
    -0.38
    isDirectory
    -0.37
    geving
    -0.36
    aimana
    -0.36
    IRQn
    -0.36
    POSITIVE LOGITS
     help
    0.90
     помощью
    0.85
    ilfe
    0.85
     Hilfe
    0.81
     behulp
    0.81
     pomocą
    0.79
     допомогою
    0.79
     pomocou
    0.78
    help
    0.78
    aided
    0.76
    Act Density 0.008%

    No Known Activations