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

    Neuronpedia

    INDEX
    Explanations

    words expressing positive sentiments or fortunate situations

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

    Expressing relief or gratitude

    np_acts-logits-general · gemini-2.0-flash

    introducing fortunate outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    makeConstraints
    -0.42
    middot
    -0.38
    TagMode
    -0.38
    󠁴
    -0.36
     bloemen
    -0.36
    stateProvider
    -0.36
     hostile
    -0.35
     Lettre
    -0.35
     lettres
    -0.34
    AppComponent
    -0.34
    POSITIVE LOGITS
    Thankfully
    0.85
     Thankfully
    0.81
    Fortunately
    0.81
    Luckily
    0.79
    幸好
    0.79
    fortunately
    0.78
     fortunately
    0.76
     thankfully
    0.76
     Luckily
    0.74
     luckily
    0.73
    Act Density 0.165%

    No Known Activations