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

    Neuronpedia

    INDEX
    Explanations

    sentences discussing the features or characteristics of an object

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.99
     فريبيس
    -0.81
     nonUne
    -0.78
    脚注の使い方
    -0.77
    protoimpl
    -0.73
    verwijspagina
    -0.72
    ']}
    -0.71
     beginnetje
    -0.70
    %</
    -0.66
     ujednoznacz
    -0.66
    POSITIVE LOGITS
     He
    0.56
     is
    0.53
    He
    0.48
     comigo
    0.48
     was
    0.46
     stør
    0.46
     
    0.45
     segítség
    0.45
     automatiques
    0.45
     His
    0.44
    Act Density 0.177%

    No Known Activations