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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases indicating relationships, comparisons, or connections

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

    conjunctions and descriptive phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    -0.53
     /
    -0.47
     .
    -0.44
     Gries
    -0.43
     :
    -0.42
     Also
    -0.41
    fromnode
    -0.41
    lio
    -0.40
    met
    -0.40
    '.
    -0.39
    POSITIVE LOGITS
     autorytatywna
    0.67
    verwijspagina
    0.64
     חיצוניים
    0.62
    batore
    0.61
     ſei
    0.58
    MLLoader
    0.57
    OGND
    0.57
     eſt
    0.56
     defaultstate
    0.55
    脚注の使い方
    0.54
    Act Density 0.110%

    No Known Activations