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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "anyway" used to transition or summarize thoughts

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

    introduces a new topic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ---|---|
    -0.47
    الإنجليزية
    -0.46
    서는
    -0.42
    ECS
    -0.42
     Gemeinsame
    -0.41
     Gates
    -0.41
     UITableViewCell
    -0.41
    machus
    -0.41
     mè
    -0.41
    refront
    -0.41
    POSITIVE LOGITS
    Anyway
    0.77
     Anyway
    0.75
     Anyways
    0.71
    Anyways
    0.70
     anyways
    0.62
     anyway
    0.62
    anyway
    0.61
    Anyhow
    0.60
     anyhow
    0.50
    Whatever
    0.49
    Act Density 0.014%

    No Known Activations