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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating specific examples or classifications within a broader context

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

    one of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.58
     EconPapers
    -0.58
    RTGC
    -0.56
     jsPsych
    -0.52
    sidemargin
    -0.51
    afficheront
    -0.51
    oredCriteria
    -0.49
    tagHelperRunner
    -0.48
    GEBURTSDATUM
    -0.48
    "]);
    -0.48
    POSITIVE LOGITS
     satunya
    0.44
    antaranya
    0.44
    期刊论文
    0.39
     instance
    0.39
    üsü
    0.39
    将其
    0.37
     namelijk
    0.35
    为例
    0.35
    voorbeeld
    0.35
    舺
    0.35
    Act Density 0.036%

    No Known Activations