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

    Neuronpedia

    INDEX
    Explanations

    The neuron activates on numerical locants (digits and related punctuation) in chemical compound names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    tokens that are parts of systematic chemical compound names (IUPAC-style fragments, numbers and hyphenated segments).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    ADATA
    -0.07
    %.
    -0.07
    PL
    -0.07
    Browser
    -0.07
    builder
    -0.07
     realizing
    -0.07
    -corner
    -0.06
    FM
    -0.06
     année
    -0.06
    ENA
    -0.06
    POSITIVE LOGITS
     введ
    0.07
    setq
    0.07
     παρ
    0.06
     bachelor
    0.06
     containerView
    0.06
     ε�
    0.06
    ↵
    0.06
     --------------------------------------------------------------------------------
    0.06
     krij
    0.06
     �
    0.06
    Act Density 0.184%

    No Known Activations