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

    Neuronpedia

    INDEX
    Explanations

    references to collective knowledge and consensus on social or political issues

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

    Sentences starting with "we"

    np_acts-logits-general · gemini-2.0-flash

    we are witnessing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     myſelf
    -0.73
     الحره
    -0.69
    yntaxException
    -0.68
    webElementGuid
    -0.67
    AsUp
    -0.66
     pinulongan
    -0.64
    tées
    -0.64
     itſelf
    -0.63
     themſelves
    -0.62
     chofe
    -0.62
    POSITIVE LOGITS
     witnessing
    0.73
     seeing
    0.67
     see
    0.67
     witnessed
    0.67
    ########.
    0.65
     witness
    0.65
     witnesses
    0.60
     شاهد
    0.59
     seen
    0.59
     saw
    0.59
    Act Density 0.195%

    No Known Activations