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

    Neuronpedia

    INDEX
    Explanations

    conversational and informal expressions

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

    Follows periods and punctuation, often starts a new sentence

    np_acts-logits-general · gemini-2.0-flash

    end of sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.72
     الرياضيه
    -0.71
    Autoritní
    -0.59
    UnsafeEnabled
    -0.59
    Билгалдахарш
    -0.59
    Personensuche
    -0.58
    AndEndTag
    -0.55
    Viited
    -0.55
    帖最后由
    -0.54
    PageRoute
    -0.53
    POSITIVE LOGITS
    Anyway
    2.73
     Anyway
    2.66
    anyway
    2.44
     Anyways
    2.41
     anyway
    2.40
    Anyways
    2.39
     anyways
    2.24
    Anyhow
    2.08
     anyhow
    1.80
     digress
    1.64
    Act Density 0.220%

    No Known Activations