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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal opinions or recommendations

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

    Following first-person pronouns, expressing thanks, or related to "I"

    np_acts-logits-general · gemini-2.0-flash

    I expressed positive sentiment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.73
    出版年
    -0.64
    adaptiveStyles
    -0.64
    <?
    -0.55
    Geplaatst
    -0.53
     nakalista
    -0.53
    })`
    -0.52
    TypedDataSet
    -0.52
    $_['
    -0.51
    StateList
    -0.51
    POSITIVE LOGITS
     highly
    0.86
     appreciated
    0.83
     Highly
    0.78
     appreciate
    0.75
    Highly
    0.73
    highly
    0.70
     greatly
    0.65
     appreci
    0.65
     HIGH
    0.63
     appreciation
    0.63
    Act Density 0.093%

    No Known Activations