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

    Neuronpedia

    INDEX
    Explanations

    supernatural

    np_max-act · gemini-2.0-flash

    behaviors that indicate insensitivity towards others' well-being.

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

    The neuron activates on mentions of “supernatural.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    725
    -0.07
    ência
    -0.06
     taxis
    -0.06
    ppy
    -0.06
    cak
    -0.06
    .bias
    -0.06
    InstanceState
    -0.06
     TArray
    -0.06
    cai
    -0.06
    $request
    -0.06
    POSITIVE LOGITS
     Prostitutas
    0.07
     drill
    0.07
     Download
    0.06
     ceiling
    0.06
    '"
    0.06
    navbarSupportedContent
    0.06
    Reporting
    0.06
    .Diagnostics
    0.06
     superintendent
    0.06
     Drill
    0.06
    Act Density 0.001%

    No Known Activations