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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing satisfaction and positive expectations about progress or success

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

    phrases and continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    retudo
    -0.45
     robustness
    -0.44
    GEBURTSDATUM
    -0.43
     Soho
    -0.43
     transformative
    -0.41
    StreetMap
    -0.41
     provocation
    -0.41
     civilisation
    -0.41
    umbai
    -0.41
    AccessFile
    -0.40
    POSITIVE LOGITS
     department
    0.44
     locally
    0.43
    essoal
    0.43
    locally
    0.42
     staff
    0.42
     kics
    0.41
     county
    0.41
    Locally
    0.41
     good
    0.40
    ఔ
    0.40
    Act Density 0.024%

    No Known Activations