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

    Neuronpedia

    INDEX
    Explanations

    any

    np_max-act · gemini-2.0-flash

    content related to financial trading practices and tools.

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

    This neuron detects liability-disclaimer language, particularly phrases saying “not responsible for any…” or similar statements of non-responsibility.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Requirements
    -0.08
     Harvard
    -0.07
     питания
    -0.06
     burning
    -0.06
    .Pass
    -0.06
     ochran
    -0.06
     bearer
    -0.06
    .Write
    -0.06
     Schneider
    -0.06
     Raf
    -0.06
    POSITIVE LOGITS
    .emplace
    0.06
    �
    0.06
    _ACTION
    0.06
    __↵
    0.06
     Στο
    0.06
    __(*
    0.06
    0.06
    implode
    0.06
    -‐
    0.06
    <?↵
    0.06
    Act Density 0.005%

    No Known Activations