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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating intent or purpose

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    XmlAccessorType
    -0.71
    --){
    -0.70
    prefixer
    -0.69
    ActionCreators
    -0.68
    ArrowToggle
    -0.66
     BoxDecoration
    -0.66
    usermodel
    -0.64
    oneofs
    -0.64
     BorderRadius
    -0.64
     protoimpl
    -0.63
    POSITIVE LOGITS
     intended
    1.25
     Intended
    1.18
    intended
    1.15
    Intended
    1.06
    Authorized
    0.95
     authorized
    0.94
    authorized
    0.94
     arrangement
    0.87
     Arrangement
    0.85
     authorised
    0.82
    Act Density 0.066%

    No Known Activations