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

    Neuronpedia

    INDEX
    Explanations

    phrases that introduce lists or examples

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

    here are/is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     PLATFORM
    -0.37
     bicchiere
    -0.36
    iſen
    -0.35
     chopped
    -0.35
    chopped
    -0.34
    Assim
    -0.34
    แน
    -0.33
     morire
    -0.33
    tester
    -0.33
    ighbor
    -0.32
    POSITIVE LOGITS
    rungsseite
    0.71
    Autoritní
    0.65
     autorytatywna
    0.63
    httphttps
    0.60
    OGND
    0.60
    plaatst
    0.52
     typelib
    0.51
    tanleria
    0.51
    niająca
    0.51
     considérons
    0.51
    Act Density 0.014%

    No Known Activations