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

    Neuronpedia

    INDEX
    Explanations

    repeated uses of the word "that."

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

    the pronoun "that" in various contexts

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

    relative pronoun clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Drapeau
    -0.70
    volving
    -0.69
     NSCoder
    -0.65
     CreateTagHelper
    -0.64
     محفوظة
    -0.63
    Bronnen
    -0.61
    ⬜
    -0.60
    AddTagHelper
    -0.59
    AnimationsModule
    -0.58
    MessageState
    -0.58
    POSITIVE LOGITS
     whom
    0.88
     who
    0.87
    whom
    0.71
     createSlice
    0.60
     câte
    0.59
    who
    0.59
     want
    0.58
     kteří
    0.57
     ktorí
    0.57
     whofe
    0.52
    Act Density 0.060%

    No Known Activations