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

    Neuronpedia

    INDEX
    Explanations

    quotable statements and phrases that reflect wisdom or life lessons

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

    ending punctuation or quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InputBorder
    -0.69
    tagHelperRunner
    -0.65
     يتيمه
    -0.62
    addCriterion
    -0.58
    flage
    -0.56
     vooz
    -0.56
     propOrder
    -0.56
     ſehr
    -0.56
     ſoll
    -0.55
    ApiModelProperty
    -0.54
    POSITIVE LOGITS
    setArguments
    0.48
    Sam
    0.42
     Sam
    0.40
    setHorizontal
    0.38
    Ben
    0.38
     Samuel
    0.37
    col
    0.37
     American
    0.37
     col
    0.37
    <h1>
    0.37
    Act Density 0.043%

    No Known Activations