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

    Neuronpedia

    INDEX
    Explanations

    connections between actions and consequences related to financial or social obligations

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

    Followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    non-english or multilingual content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     justement
    -1.04
     oftentimes
    -0.95
     basically
    -0.93
     appunto
    -0.92
     nemlig
    -0.92
     destul
    -0.91
     effectivement
    -0.90
     Namely
    -0.89
     assolutamente
    -0.87
    basically
    -0.87
    POSITIVE LOGITS
    何况
    0.55
    我喜欢
    0.54
    二是
    0.51
     चाहिए
    0.47
    下が
    0.47
     چون
    0.46
    她是
    0.46
    変わる
    0.46
    ugal
    0.46
    ちは
    0.46
    Act Density 1.402%

    No Known Activations