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

    Neuronpedia

    INDEX
    Explanations

    specific character patterns or phonetic structures in words and phrases

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

    ending in "ee," "oo," or starting with "B"

    np_acts-logits-general · gemini-2.0-flash

    sounds or rhyming words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wharton
    -0.47
     eiland
    -0.47
    mantec
    -0.44
    mfenced
    -0.44
    nteral
    -0.44
     Ralf
    -0.42
    vertx
    -0.41
     }],
    -0.41
     Lamont
    -0.41
     Walther
    -0.41
    POSITIVE LOGITS
    oo
    1.06
    Bee
    1.02
    lee
    1.02
    boo
    1.00
    bee
    0.98
    Boo
    0.96
     Bee
    0.94
    Doo
    0.93
     Coo
    0.93
    Moo
    0.93
    Act Density 0.825%

    No Known Activations