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

    Neuronpedia

    INDEX
    Explanations

    positive and negative sentiments related to situations or events

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

    fortunate or unfortunate circumstances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تعدى
    -0.56
     BytesLike
    -0.54
    Erreferentziak
    -0.52
    ätie
    -0.50
    WithIOException
    -0.50
    ьаж
    -0.50
    曖昧さ回避
    -0.50
    setContentView
    -0.50
    parsedMessage
    -0.50
     bezeichneter
    -0.49
    POSITIVE LOGITS
    Fortunately
    0.60
    好在
    0.57
     Fortunately
    0.57
     fortunately
    0.54
    可惜
    0.54
    幸好
    0.53
    fortunately
    0.52
    Luckily
    0.51
    奈何
    0.49
     Luckily
    0.49
    Act Density 0.031%

    No Known Activations