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

    Neuronpedia

    INDEX
    Explanations

    specific terms and keywords related to regulations, scientific research, and various classifications of people or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AppBundle
    -0.56
    ثيق
    -0.56
     gând
    -0.54
     gefe
    -0.52
    tså
    -0.50
     asiatique
    -0.50
    UnknownFieldSet
    -0.49
    ISupport
    -0.49
     Walkover
    -0.49
    Innen
    -0.49
    POSITIVE LOGITS
    __':
    0.63
    s
    0.60
     CanadaChoose
    0.59
    __":
    0.56
    solutions
    0.56
    __':
    0.54
    
    0.54
     CURIAM
    0.52
    ]!='
    0.52
    ÓW
    0.50
    Act Density 0.419%

    No Known Activations