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

    Neuronpedia

    INDEX
    Explanations

    affirmative responses and confirmations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    webElement
    -0.77
    +#+
    -0.71
    hical
    -0.61
    ?».
    -0.60
    enumii
    -0.59
    trane
    -0.59
    Попис
    -0.59
    ⓧ
    -0.57
    }`}>
    -0.57
     aidant
    -0.57
    POSITIVE LOGITS
     YES
    0.70
     yes
    0.64
     AssemblyCulture
    0.61
    yes
    0.60
    YES
    0.59
     Yes
    0.57
    Yes
    0.56
     yup
    0.49
    会的
    0.49
     vzduchu
    0.48
    Act Density 0.067%

    No Known Activations