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

    Neuronpedia

    INDEX
    Explanations

    phrases related to procedural or systematic operations

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

    prepositions that introduce dependent clauses or phrases explaining relationships between entities or concepts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     leiding
    -0.39
     skolen
    -0.39
     geschiedenis
    -0.37
     inderdaad
    -0.35
     území
    -0.34
     değildir
    -0.34
     complètes
    -0.34
    -0.34
     religieux
    -0.33
     wezen
    -0.33
    POSITIVE LOGITS
     autorytatywna
    0.92
     betweenstory
    0.79
    contentLoaded
    0.64
    といけない
    0.64
     otomatig
    0.63
    pecabe
    0.63
    ſſung
    0.61
    <unused79>
    0.60
    [@BOS@]
    0.59
    <unused14>
    0.59
    Act Density 5.513%

    No Known Activations