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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating eligibility or options for discounts and assistance in a customer service context

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

    Beginning of sentences

    np_acts-logits-general · gemini-2.0-flash

    phrases like "due to" or "able to"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.58
     noastră
    -0.53
     ✓
    -0.49
     –
    -0.48
     bộ
    -0.45
    ább
    -0.44
     encontrarás
    -0.43
    tvguidetime
    -0.41
    〗
    -0.40
    ʼ
    -0.40
    POSITIVE LOGITS
    StoreMessageInfo
    0.89
     Connectez
    0.81
    enumi
    0.75
    FormTagHelper
    0.75
    }\\
    0.74
    ↵↵↵
    0.70
    ValueStyle
    0.69
     بيها
    0.69
    KeySpec
    0.68
    \}\\
    0.68
    Act Density 0.082%

    No Known Activations