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

    Neuronpedia

    INDEX
    Explanations

    rewrite

    np_max-act · gemini-2.0-flash

    formal and sophisticated language typical of 19th-century British gentleman discourse.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    \\
    -0.07
    ac
    -0.07
    らの
    -0.07
    ?id
    -0.07
     coloc
    -0.07
     miejsc
    -0.06
    胆
    -0.06
    z
    -0.06
     cared
    -0.06
    óż
    -0.06
    POSITIVE LOGITS
     rewriting
    0.09
     rewrite
    0.08
    ाहरण
    0.08
     Rewrite
    0.07
     agora
    0.07
    _rewrite
    0.06
     TEMPLATE
    0.06
     poisoning
    0.06
     Nha
    0.06
     FormsModule
    0.06
    Act Density 0.006%

    No Known Activations