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

    Neuronpedia

    INDEX
    Explanations

    the presence of certain pronouns and auxiliary verbs in contexts suggesting subordinate or relative clauses

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

    at which time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     agencia
    -0.37
    évaluateur
    -0.37
     agence
    -0.37
    DoubleQuotes
    -0.35
    átek
    -0.35
    OCCURRED
    -0.34
    📦
    -0.34
    intellij
    -0.33
     Tinubu
    -0.33
    Ivoire
    -0.32
    POSITIVE LOGITS
     पर
    0.82
     waarop
    0.65
    面上
    0.61
     પર
    0.60
    会上
    0.60
    子上
    0.57
    板上
    0.57
    rungsseite
    0.54
     onStart
    0.54
     CreateTagHelper
    0.54
    Act Density 0.004%

    No Known Activations