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

    Neuronpedia

    INDEX
    Explanations

    phrases questioning the value or worth of something

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

    worth the effort or outcome

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.63
    UnusedPrivate
    -0.58
     lenker
    -0.53
     ProtoMessage
    -0.53
    twimg
    -0.52
    انجليز
    -0.50
     createSlice
    -0.50
    ロウィン
    -0.50
    Tē
    -0.50
     通販
    -0.49
    POSITIVE LOGITS
     worthless
    0.43
     worth
    0.34
    worse
    0.34
    ModuleName
    0.34
    useless
    0.33
     peores
    0.32
     BeautifulSoup
    0.31
     semmi
    0.31
     WORTH
    0.31
    cheap
    0.31
    Act Density 0.012%

    No Known Activations