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

    Neuronpedia

    INDEX
    Explanations

    phrases that discuss values and beliefs

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    HasAnnotation
    -0.81
     Efq
    -0.68
    HttpFoundation
    -0.66
    providedIn
    -0.66
    abstractmethod
    -0.66
     &___
    -0.65
     Majefty
    -0.65
    GraphicsUnit
    -0.65
     tslint
    -0.65
    scriptId
    -0.65
    POSITIVE LOGITS
     protoimpl
    0.54
     '\\;'
    0.51
     grises
    0.46
     roble
    0.45
     declarat
    0.45
     
    0.44
     září
    0.42
    тости
    0.41
    یی
    0.41
     complejos
    0.40
    Act Density 0.682%

    No Known Activations