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

    Neuronpedia

    INDEX
    Explanations

    separated

    np_max-act · gemini-2.0-flash

    information related to programming or coding examples.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on words that describe splitting or delimiting items (e.g. “separated,” “separating,” “split,” “spaces”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     OrderedDict
    -0.07
    rawtypes
    -0.07
     eos
    -0.07
    اجه
    -0.06
     cuộc
    -0.06
    �
    -0.06
    lığı
    -0.06
    ujícím
    -0.06
     사람들이
    -0.06
    気持ち
    -0.06
    POSITIVE LOGITS
    ?'
    0.07
    (pin
    0.07
     Pick
    0.07
    下载
    0.07
    ?"
    0.07
    AN
    0.06
     "-"
    0.06
     Pul
    0.06
     propelled
    0.06
     topp
    0.06
    Act Density 0.004%

    No Known Activations