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

    Neuronpedia

    INDEX
    Explanations

    statements involving claims or assertions made by individuals

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

    claim followed by to or that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     IMC
    -0.60
     CRS
    -0.58
    CRS
    -0.52
     IRS
    -0.52
     Mortuary
    -0.50
     instru
    -0.50
    MEP
    -0.49
     PN
    -0.48
    SPS
    -0.48
     PSS
    -0.48
    POSITIVE LOGITS
     claimed
    0.98
     CLAIM
    0.90
     claim
    0.87
     CLAIMS
    0.83
     claiming
    0.81
     claims
    0.81
     Behaup
    0.76
     Claim
    0.75
    Claim
    0.75
    CLAIM
    0.73
    Act Density 0.037%

    No Known Activations