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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing concerns or assertions about care, relevance, and significance

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

    verbs followed by prepositions/conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    issory
    -0.56
     resourceCulture
    -0.52
    BuildContext
    -0.52
    -0.46
    EndTag
    -0.43
    genheim
    -0.43
     Италијани
    -0.42
    labus
    -0.42
    tplatz
    -0.41
     SALUD
    -0.40
    POSITIVE LOGITS
     متعلقه
    0.47
     ProtoMessage
    0.39
    دانشنامهٔ
    0.36
    balleur
    0.36
     כן
    0.35
    HasAnnotation
    0.35
    ější
    0.35
     juist
    0.34
     justru
    0.34
    RegressionTest
    0.34
    Act Density 0.755%

    No Known Activations