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

    Neuronpedia

    INDEX
    Explanations

    entities related to organizations, professions, and roles in society

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

    describing organizations and people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KommentareTeilen
    -0.72
    IVersion
    -0.59
     OMITBAD
    -0.55
    HasForeignKey
    -0.54
     resourceCulture
    -0.53
    הערות
    -0.53
     ProtoMessage
    -0.53
    SequentialGroup
    -0.53
     Downvote
    -0.52
    تقاوى
    -0.49
    POSITIVE LOGITS
     whose
    0.76
    whose
    0.62
     known
    0.57
     whom
    0.57
     who
    0.54
     formerly
    0.50
    known
    0.47
    whom
    0.47
     nicknamed
    0.46
    "]);
    0.46
    Act Density 0.049%

    No Known Activations