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

    Neuronpedia

    INDEX
    Explanations

    phrases containing repeated instances of the word "of"

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

    "A lot of" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    phrases like "a lot of"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    i
    -0.60
    or
    -0.58
     Combien
    -0.55
    I
    -0.54
    -
    -0.54
     esquerdo
    -0.54
    and
    -0.53
     szob
    -0.52
    U
    -0.52
    StoryboardSegue
    -0.51
    POSITIVE LOGITS
     these
    0.79
    UIControlState
    0.79
    "):
    0.78
     them
    0.75
     the
    0.75
    sted
    0.74
    Хьажоргаш
    0.73
     snippetHide
    0.73
     their
    0.72
     different
    0.72
    Act Density 0.212%

    No Known Activations