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

    Neuronpedia

    INDEX
    Explanations

    dialogue and conversational elements in text

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

    discourse markers and transitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HideFlags
    -0.66
     ſche
    -0.60
    IVEREF
    -0.57
    Uwaga
    -0.57
     Verſ
    -0.55
    astéro
    -0.54
     térmico
    -0.52
    UnknownFields
    -0.52
     prohibido
    -0.52
    省市镇
    -0.51
    POSITIVE LOGITS
    Anyway
    0.75
     Anyway
    0.72
     anyway
    0.66
    anyway
    0.63
     Maybe
    0.60
     utafitiHapana
    0.59
    Maybe
    0.57
     anyways
    0.56
     Yeah
    0.56
     anyhow
    0.55
    Act Density 0.164%

    No Known Activations