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

    Neuronpedia

    INDEX
    Explanations

    ignore

    np_max-act · gemini-2.0-flash

    technical terms and configurations related to network and system settings.

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

    The neuron activates on the literal token “ignore” (e.g. option names or parameters beginning with “ignore”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     transition
    -0.09
     Reef
    -0.07
     ii
    -0.07
     POST
    -0.07
    eş
    -0.07
    PostExecute
    -0.07
    birthdate
    -0.07
     exempl
    -0.07
     Sanat
    -0.06
     tooth
    -0.06
    POSITIVE LOGITS
     ignore
    0.10
     ignores
    0.09
    ignore
    0.09
    Ignore
    0.09
    .ignore
    0.09
     ignored
    0.08
     ignor
    0.08
    148
    0.08
     ire
    0.08
    IGNORE
    0.07
    Act Density 0.009%

    No Known Activations