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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate a positive outlook or good outcomes

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

    after "the" or related to "positive"

    np_acts-logits-general · gemini-2.0-flash

    positive aspects or outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nodoc
    -0.73
     beginnetje
    -0.72
    getHours
    -0.58
    //
    -0.56
     mergeFrom
    -0.56
    protoc
    -0.55
    migrationBuilder
    -0.54
     daarvoor
    -0.54
    #+#
    -0.54
     Wikimedijinoj
    -0.52
    POSITIVE LOGITS
     positive
    1.61
     positives
    1.57
     upside
    1.36
    positive
    1.33
     positif
    1.27
     silver
    1.27
    Positive
    1.24
     POSITIVE
    1.24
     Positive
    1.22
     bright
    1.19
    Act Density 0.132%

    No Known Activations