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

    Neuronpedia

    INDEX
    Explanations

    phrases that express strong recommendations

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

    recommending or suggesting things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gezet
    -0.39
    cerpt
    -0.38
    failure
    -0.37
    Unmarshaller
    -0.36
     Murillo
    -0.36
     Catalana
    -0.36
    <_>
    -0.35
     failure
    -0.35
     Acharya
    -0.35
    ger
    -0.34
    POSITIVE LOGITS
     recommend
    1.76
     Recommend
    1.50
     recommending
    1.35
    recommend
    1.34
     recommends
    1.34
    Recommend
    1.26
     RECOMMEND
    1.25
     reccomend
    1.13
     recomend
    1.12
     recommendations
    1.05
    Act Density 0.007%

    No Known Activations