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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve correction or interruption in conversation

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

    correct me if i'm wrong

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     INTERESAR
    -0.34
     Cons
    -0.33
    ślę
    -0.31
    évaluateur
    -0.31
    ItemLayout
    -0.31
     comp
    -0.31
    doi
    -0.31
    Personendaten
    -0.30
     mobili
    -0.30
     /#
    -0.30
    POSITIVE LOGITS
     ligiloj
    0.58
     contradicted
    0.57
    EndContext
    0.56
     contradicts
    0.55
     contradict
    0.52
    Atsauces
    0.52
    ReusableCell
    0.52
     EconPapers
    0.51
    المناصب
    0.51
     onCreateView
    0.50
    Act Density 0.079%

    No Known Activations