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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to credibility and trustworthiness

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

    credibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ysacchar
    -0.37
     app
    -0.36
     oct
    -0.36
     Sart
    -0.36
     laws
    -0.35
     Quar
    -0.34
     compor
    -0.34
     defaultstate
    -0.33
     sot
    -0.33
     ass
    -0.33
    POSITIVE LOGITS
     credibility
    1.91
    dibility
    1.69
     credible
    1.65
    credi
    1.45
     credi
    1.27
     CRED
    1.21
     creditable
    1.01
     glaub
    0.99
    dible
    0.97
     Glaub
    0.94
    Act Density 0.007%

    No Known Activations